{"slug": "gemini", "name": "Gemini", "category": "ai", "category_name": "AI models and assistants", "description": "Google's family of AI models and chatbot assistant, available on web, mobile and API.", "recommenders": 168, "commenters": 435, "warners": 98, "score": 103.243, "rising": 29.33, "first": "2025-11-08", "latest": "2026-10-31", "why": "HN commenters like Gemini for fast, search-style everyday questions, non-coding research and learning, and OCR or data extraction.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 180, "neutral": 156, "compare": 29, "warn": 103}, "spark": [13, 16, 14, 14, 6, 6, 5, 21, 18, 18, 31, 18], "listed": true, "loved": ["Non-coding tasks", "Search replacement"], "caveat": "Coding and agents", "short_quote": "I just recently switched from using Siri to Google Gemini in my car. The experience is dramatically better.", "icon": true, "domain": "google.dev", "github_repo": null, "official_url": "https://gemini.google.com", "pricing": "freemium", "aliases": ["Gemini", "Gemini 3", "Google Gemini", "Gemini 3.0", "Gemini 3.1", "Gemini 3.5", "Gemini 3.8"], "verdict": [{"text": "HN commenters like Gemini for fast, search-style everyday questions", "cites": [{"id": 795476432, "item_id": 49717277, "url": "https://news.ycombinator.com/item?id=49717277", "by": "mvdtnz", "date": "2026-09-15", "stance": "recommend", "quote": "it's my go-to for just searching basic information (replacing google search) because it's so darn fast", "excerpt": "My Gemini app is still stuck at 3.5 Flash-lite and 3.6 Flash so I truly don't understand how Google rolls this stuff out. I don't use Gemini for anything serious so I'm not going to use the API, but it's my go-to for just searching basic information (replacing google search) because it's so darn fast.", "context": "", "use_case": "quick information search", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 795512144, "item_id": 49719509, "url": "https://news.ycombinator.com/item?id=49719509", "by": "Keyframe", "date": "2026-09-15", "stance": "recommend", "quote": "I've been using gemini personally instead of what I used regular google searches for the better part.", "excerpt": "Anecdata, but I've been using gemini personally instead of what I used regular google searches for the better part. Even in car chat/search and some lighter and not so light research (if it's not heavy on technicals). It's good enough that I use it nonstop like that. I wouldn't trust it for coding at all - switching between fable and now astra. Google in a sense won (me over) like that. I also expected them to brute ", "context": "", "use_case": "search and light research", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 804616736, "item_id": 50288546, "url": "https://news.ycombinator.com/item?id=50288546", "by": "bayindirh", "date": "2026-10-29", "stance": "recommend", "quote": "I find myself using it more than Claude.", "excerpt": "People always love to think the AI race is a duopoly (OpenAI vs. Anthropic), but from what I have experienced, Gemini was always holding on its own, and I find myself using it more than Claude. True, I use LLMs as glorified search engines to unearth material to read myself, but Gemini is much more useful if you decide to learn yourself. It also offers interesting expansions to your questions. While I don't offload my", "context": "uses LLMs as glorified search engines", "use_case": "research and learning", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}]}, {"text": ", non-coding research and learning", "cites": [{"id": 804675825, "item_id": 50292239, "url": "https://news.ycombinator.com/item?id=50292239", "by": "TacticalCoder", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini is also IMO excellent for everything that is not coding.", "excerpt": "Not a moat and not big but... for SMEs \"Google Workspace\" is a godsend from outter space. This is what allow little SMEs to not have to suffer that piece of shit that Windows is. I know people running their SMEs (and I helped them set up Google Workspace) from Mac and Chromebooks since years and years and who do not ever want to here again from anything Microsoft. They're basically doing everything inside \"Google Wor", "context": "pays for an Anthropic subscription", "use_case": "non-coding tasks", "switched_from": "", "story": "Google Search is now less than half of Alphabet\u2019s revenue"}, {"id": 795588320, "item_id": 49724270, "url": "https://news.ycombinator.com/item?id=49724270", "by": "paride5745", "date": "2026-09-16", "stance": "recommend", "quote": "I use gemini for everything not-coding", "excerpt": "Same here. I use gemini for everything not-coding, from doing research, to have custom personas for more niche topics (and feeding more detailed knowledge in these cases). For coding and image editing, right now I find ChatGPT superior. And for software architecture designs or planning Claude is the best since a while. I still have to try Grok to be fair.", "context": "", "use_case": "research, personas, non-coding tasks", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 794784401, "item_id": 49674025, "url": "https://news.ycombinator.com/item?id=49674025", "by": "george_stephen", "date": "2026-09-12", "stance": "recommend", "quote": "Gemini for academic work to encyclopedia and know-how discussions", "excerpt": "I use all of em, ChatGPT 5.6luna ion web, for quick tasks(without signup), (ii personally feel ChatGPT isn't straightforward especially when quizing its opinion on a topic) , Gemini for academic work to encyclopedia and know-how discussions, recommending solutions to technical tasks by looking up web for me(it's my primary driver, but lags behind in coding abilities,its large context is a plus. I recently started ret", "context": "", "use_case": "academic work and research", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}]}, {"text": ", and OCR or data extraction.", "cites": [{"id": 804621056, "item_id": 50288816, "url": "https://news.ycombinator.com/item?id=50288816", "by": "sgc", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini has and does absolutely dominate for this.", "excerpt": "For ocr, you have to practice, practice, practice with your prompts on small sample sizes before one-shotting a book. I create a json schema for the output that describes the structure in detail (using ai from my prose descriptions of structure of course). I have specific tough pages I use on openrouter to test every new model I am interested in. Gemini has and does absolutely dominate for this. But flash can be bett", "context": "", "use_case": "OCR of books", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 803909682, "item_id": 50244355, "url": "https://news.ycombinator.com/item?id=50244355", "by": "mathewjacob", "date": "2026-10-26", "stance": "recommend", "quote": "Gemini web which had the best OCR + context window combo at the time", "excerpt": "I've built what I believe is currently the best free, online resource for learning Malayalam from scratch. It is based on a textbook and related materials made available by the University of Texas at Austin (UT) which are available under the Creative Commons License. It is a full University course with grammar lessons, vocabulary, and audio clips. I've used those to also build Anki decks for flash cards. A significan", "context": "", "use_case": "OCR of textbook", "switched_from": "", "story": "Malayalam: A University Course"}, {"id": 798700450, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "warn", "quote": "I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else.", "excerpt": "While that\u2019s true, I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else. I pay for lots of models because they\u2019re good at different things: $20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t, but I\u2019m yet to have any Gemini model find a real bug, and Gemini\u2019s results for general work will sometim", "context": "", "use_case": "data extraction", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}]}, {"text": " The most common complaints are confidently wrong or hallucinated answers", "cites": [{"id": 800484864, "item_id": 50030304, "url": "https://news.ycombinator.com/item?id=50030304", "by": "literalAardvark", "date": "2026-10-10", "stance": "warn", "quote": "Please note that Gemini has a habit of \"confident slight misremembering\".", "excerpt": "I didn't know what your example was, so I used AI in one of the best ways it can be used today: I googled \"Mel's famous chess demo\" and it blurted out this beautiful thing, which I am sharing here for discussion context: \"Mel's famous chess demo\" appears to be a slight misremembering of the legendary hacker folklore epic, The Story of Mel. In the actual story, the \"Real Programmer\" named Mel Kaye didn't code a chess ", "context": "", "use_case": "answering search queries", "switched_from": "", "story": "Programming Isn't Special"}, {"id": 799102673, "item_id": 49943917, "url": "https://news.ycombinator.com/item?id=49943917", "by": "user2722", "date": "2026-10-03", "stance": "warn", "quote": "Google's Gemini hallucinated spots or imagined details", "excerpt": "I moved from a densely populated area to a more sparse one. I'll probably renew Kagi because its assistant can answer my questions, such as: \"find me a location where I can be on my computer but also public where I can also be with a group of people\". Google's Gemini hallucinated spots or imagined details -- at one point it included a shed in the middle of a road -- the shed existed, nothing else did. DDG did similar", "context": "", "use_case": "finding locations", "switched_from": "", "story": "An Update on Orion for Linux and Windows"}, {"id": 797938192, "item_id": 49871137, "url": "https://news.ycombinator.com/item?id=49871137", "by": "hnbad", "date": "2026-09-27", "stance": "warn", "quote": "Literally every experience I've had with Gemini / Google Search AI answers followed this exact pattern", "excerpt": "Literally every experience I've had with Gemini / Google Search AI answers followed this exact pattern, often repeated several times more if I remained persistent instead of just giving up. Typical example: \"Where can I buy <thing I'm looking for that I can't find anywhere using normal search terms>?\" > You're looking for <related but different and widely available thing>. It is sold by <sites I never heard of>. \"No,", "context": "", "use_case": "product search", "switched_from": "", "story": "When did Google get so weird?"}, {"id": 799972512, "item_id": 49998282, "url": "https://news.ycombinator.com/item?id=49998282", "by": "svnt", "date": "2026-10-07", "stance": "warn", "quote": "It is one thing to avoid sycophancy, but Gemini often seems to go well beyond that.", "excerpt": "Gemini has been like that. One early model I used I asked it about another company\u2019s model. It insisted it didn\u2019t exist. I told it when it was released and to search. It did, and found results, but told me it wasn\u2019t really a public model and I couldn\u2019t use it. I screenshotted the pricing page. It told me I got that from somewhere else, it couldn\u2019t be correct, because it couldn\u2019t access that page. It is one thing to a", "context": "", "use_case": "", "switched_from": "", "story": "AI Model Groupthink"}]}, {"text": " and weak coding and agentic performance.", "cites": [{"id": 801186256, "item_id": 50074141, "url": "https://news.ycombinator.com/item?id=50074141", "by": "ralusek", "date": "2026-10-13", "stance": "recommend", "quote": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes.", "excerpt": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes. I never touch 3.8, it's awful. Curious to try this, but I've yet to use any Gemini that is good for agentic work. Also, unrelated but this made me look at Artificial Analysis to see where it lands on Cost per Task, and it ranks Opus 5.5 at almost double Astra 6. That does not align with my experience.", "context": "", "use_case": "primary chatbot", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 795512144, "item_id": 49719509, "url": "https://news.ycombinator.com/item?id=49719509", "by": "Keyframe", "date": "2026-09-15", "stance": "recommend", "quote": "I've been using gemini personally instead of what I used regular google searches for the better part.", "excerpt": "Anecdata, but I've been using gemini personally instead of what I used regular google searches for the better part. Even in car chat/search and some lighter and not so light research (if it's not heavy on technicals). It's good enough that I use it nonstop like that. I wouldn't trust it for coding at all - switching between fable and now astra. Google in a sense won (me over) like that. I also expected them to brute ", "context": "", "use_case": "search and light research", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 798700450, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "warn", "quote": "I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else.", "excerpt": "While that\u2019s true, I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else. I pay for lots of models because they\u2019re good at different things: $20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t, but I\u2019m yet to have any Gemini model find a real bug, and Gemini\u2019s results for general work will sometim", "context": "", "use_case": "data extraction", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}, {"id": 797690595, "item_id": 49855662, "url": "https://news.ycombinator.com/item?id=49855662", "by": "assimpleaspossi", "date": "2026-09-26", "stance": "warn", "quote": "The code they supplied to me has NEVER worked or was so convoluted that I threw it away and did it myself.", "excerpt": "I find it strange to see people writing articles like this as if everyone has used AI for decades. I've programmed for decades. I thought I retired three years ago but got an offer I couldn't refuse. Already there were little things I'd forgotten how to use. Over the past six months I tried using Claude, chatgpt, Grok and Gemini. At best I got reminders of how things worked. People online say they use them to write t", "context": "", "use_case": "coding help", "switched_from": "", "story": "One Month Without AI"}]}], "praise": [{"label": "Non-coding tasks", "summary": "Several commenters use it for research, learning and general questions outside of coding.", "quotes": [{"id": 804675825, "item_id": 50292239, "url": "https://news.ycombinator.com/item?id=50292239", "by": "TacticalCoder", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini is also IMO excellent for everything that is not coding.", "excerpt": "Not a moat and not big but... for SMEs \"Google Workspace\" is a godsend from outter space. This is what allow little SMEs to not have to suffer that piece of shit that Windows is. I know people running their SMEs (and I helped them set up Google Workspace) from Mac and Chromebooks since years and years and who do not ever want to here again from anything Microsoft. They're basically doing everything inside \"Google Wor", "context": "pays for an Anthropic subscription", "use_case": "non-coding tasks", "switched_from": "", "story": "Google Search is now less than half of Alphabet\u2019s revenue"}, {"id": 795588320, "item_id": 49724270, "url": "https://news.ycombinator.com/item?id=49724270", "by": "paride5745", "date": "2026-09-16", "stance": "recommend", "quote": "I use gemini for everything not-coding", "excerpt": "Same here. I use gemini for everything not-coding, from doing research, to have custom personas for more niche topics (and feeding more detailed knowledge in these cases). For coding and image editing, right now I find ChatGPT superior. And for software architecture designs or planning Claude is the best since a while. I still have to try Grok to be fair.", "context": "", "use_case": "research, personas, non-coding tasks", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 804616736, "item_id": 50288546, "url": "https://news.ycombinator.com/item?id=50288546", "by": "bayindirh", "date": "2026-10-29", "stance": "recommend", "quote": "I find myself using it more than Claude.", "excerpt": "People always love to think the AI race is a duopoly (OpenAI vs. Anthropic), but from what I have experienced, Gemini was always holding on its own, and I find myself using it more than Claude. True, I use LLMs as glorified search engines to unearth material to read myself, but Gemini is much more useful if you decide to learn yourself. It also offers interesting expansions to your questions. While I don't offload my", "context": "uses LLMs as glorified search engines", "use_case": "research and learning", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}]}, {"label": "Search replacement", "summary": "Some use it instead of regular Google searches for basic information and lighter research.", "quotes": [{"id": 795512144, "item_id": 49719509, "url": "https://news.ycombinator.com/item?id=49719509", "by": "Keyframe", "date": "2026-09-15", "stance": "recommend", "quote": "I've been using gemini personally instead of what I used regular google searches for the better part.", "excerpt": "Anecdata, but I've been using gemini personally instead of what I used regular google searches for the better part. Even in car chat/search and some lighter and not so light research (if it's not heavy on technicals). It's good enough that I use it nonstop like that. I wouldn't trust it for coding at all - switching between fable and now astra. Google in a sense won (me over) like that. I also expected them to brute ", "context": "", "use_case": "search and light research", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 795476432, "item_id": 49717277, "url": "https://news.ycombinator.com/item?id=49717277", "by": "mvdtnz", "date": "2026-09-15", "stance": "recommend", "quote": "it's my go-to for just searching basic information (replacing google search) because it's so darn fast", "excerpt": "My Gemini app is still stuck at 3.5 Flash-lite and 3.6 Flash so I truly don't understand how Google rolls this stuff out. I don't use Gemini for anything serious so I'm not going to use the API, but it's my go-to for just searching basic information (replacing google search) because it's so darn fast.", "context": "", "use_case": "quick information search", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 800422784, "item_id": 50026424, "url": "https://news.ycombinator.com/item?id=50026424", "by": "ButlerianJihad", "date": "2026-10-09", "stance": "recommend", "quote": "Gemini is really good about surfacing summaries and overviews and answering thorny questions", "excerpt": "I found the consumer facing \"tax professionals\" to be indifferent and apparently, nearly incompetent. Like, I walked into a tax office in my neighborhood and the certified dude could not answer a question without typing it into the Search Box on his computer. In contrast, I found Gemini to be pretty good at directing me to verify my own answers at IRS.gov. It was able to answer correctly but of course, Gemini is not ", "context": "", "use_case": "tax questions", "switched_from": "", "story": "Ask HN: Why hasn't AI replaced Tax filing software"}]}, {"label": "OCR and extraction", "summary": "Praised for OCR, data extraction and video transcription.", "quotes": [{"id": 804621056, "item_id": 50288816, "url": "https://news.ycombinator.com/item?id=50288816", "by": "sgc", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini has and does absolutely dominate for this.", "excerpt": "For ocr, you have to practice, practice, practice with your prompts on small sample sizes before one-shotting a book. I create a json schema for the output that describes the structure in detail (using ai from my prose descriptions of structure of course). I have specific tough pages I use on openrouter to test every new model I am interested in. Gemini has and does absolutely dominate for this. But flash can be bett", "context": "", "use_case": "OCR of books", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 803909682, "item_id": 50244355, "url": "https://news.ycombinator.com/item?id=50244355", "by": "mathewjacob", "date": "2026-10-26", "stance": "recommend", "quote": "Gemini web which had the best OCR + context window combo at the time", "excerpt": "I've built what I believe is currently the best free, online resource for learning Malayalam from scratch. It is based on a textbook and related materials made available by the University of Texas at Austin (UT) which are available under the Creative Commons License. It is a full University course with grammar lessons, vocabulary, and audio clips. I've used those to also build Anki decks for flash cards. A significan", "context": "", "use_case": "OCR of textbook", "switched_from": "", "story": "Malayalam: A University Course"}, {"id": 801353968, "item_id": 50084623, "url": "https://news.ycombinator.com/item?id=50084623", "by": "jakderrida", "date": "2026-10-14", "stance": "recommend", "quote": "you can plug it into any gemini and have it transcribe and diarize the video.", "excerpt": "If a video is less than 45 minutes, you can plug it into any gemini and have it transcribe and diarize the video. (although, I've been told it only works on aistudio anymore) Sometimes it trips up. However, plugging in videos longer than 45 minutes quickly leads to ludicrous behavior the longer it is over 45 minutes. You can even just plug in the Youtube link with a short prompt. Bear in mind that thinking that plugg", "context": "", "use_case": "video transcription and diarization", "switched_from": "", "story": "Show HN: I built a tool to track what AI leaders say and how their views change"}]}, {"label": "Daily driver", "summary": "Some commenters use it all day and call it solid or a fine workhorse.", "quotes": [{"id": 801236976, "item_id": 50077311, "url": "https://news.ycombinator.com/item?id=50077311", "by": "jeffrallen", "date": "2026-10-13", "stance": "recommend", "quote": "I use Gemini all day at work via the chat interface. It's rock solid.", "excerpt": "I use Gemini all day at work via the chat interface. It's rock solid. I find it hard to understand which model it's using though. Am I already using Argon, or does it switch models according to the subject?", "context": "", "use_case": "work chat assistant", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 800091872, "item_id": 50005742, "url": "https://news.ycombinator.com/item?id=50005742", "by": "HelloMcFly", "date": "2026-10-08", "stance": "recommend", "quote": "I use Gemini more than any other model at the moment", "excerpt": "I use Gemini more than any other model at the moment, I have absolutely no idea what you're talking about with this experience.", "context": "", "use_case": "", "switched_from": "", "story": "GPT\u20116 and Intelligent UI for everyone"}, {"id": 798636288, "item_id": 49914768, "url": "https://news.ycombinator.com/item?id=49914768", "by": "nozzlegear", "date": "2026-09-30", "stance": "recommend", "quote": "It was a fine workhorse IMO, no complaints from me.", "excerpt": "> A good consideration; just one point from my side: as far as I am aware (but I may be wrong), Gemini is not known to perform well in an agentic framework. I used it for a month over the summer, right before they were going through the migration to antigravity. It was a fine workhorse IMO, no complaints from me.", "context": "used it for a month over the summer", "use_case": "agentic work", "switched_from": "", "story": "Gemini 4 Argon"}]}, {"label": "Speed", "summary": "Commenters note that it responds quickly, especially the Flash models.", "quotes": [{"id": 795476432, "item_id": 49717277, "url": "https://news.ycombinator.com/item?id=49717277", "by": "mvdtnz", "date": "2026-09-15", "stance": "recommend", "quote": "it's my go-to for just searching basic information (replacing google search) because it's so darn fast", "excerpt": "My Gemini app is still stuck at 3.5 Flash-lite and 3.6 Flash so I truly don't understand how Google rolls this stuff out. I don't use Gemini for anything serious so I'm not going to use the API, but it's my go-to for just searching basic information (replacing google search) because it's so darn fast.", "context": "", "use_case": "quick information search", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 797300688, "item_id": 49831293, "url": "https://news.ycombinator.com/item?id=49831293", "by": "TomGarden", "date": "2026-09-24", "stance": "recommend", "quote": "I enjoy the speed of Gemini", "excerpt": "yeah I enjoy the speed of Gemini, but I also just have the low tier one (I use the 20x Claude and Codex subs for most of my work). For iteration, Gemini is so much fun, but Opus 5.5 is quite fast, as is sol. If you're on a budget, deepseek does look great", "context": "", "use_case": "fast iteration", "switched_from": "", "story": "Best LLM for every budget, updated daily"}, {"id": 804586192, "item_id": 50286637, "url": "https://news.ycombinator.com/item?id=50286637", "by": "hypendev", "date": "2026-10-29", "stance": "recommend", "quote": "I use their models and for my niche they are the best for good quality at great speeds.", "excerpt": "I was confused a bit where this was. Then I had to Google Gemini, which lead me to gemini.google.com (did not know it existed, and I use gemini in prod via google cloud). First thing there that got me was that all of my Google searches. Why? I googled \"snoop dog real name\". Why is this considered a gemini chat now? If I actually used it, my chats would be buried under dumb quick google searches I did. And it seems it", "context": "uses Gemini in prod via Google Cloud", "use_case": "production app via API", "switched_from": "", "story": "Gemini 4 Carbon"}]}, {"label": "In-car use", "summary": "Users like it in Google Maps and Android Auto on drives.", "quotes": [{"id": 795516176, "item_id": 49719761, "url": "https://news.ycombinator.com/item?id=49719761", "by": "asdfman123", "date": "2026-09-15", "stance": "recommend", "quote": "I love Gemini in Google Maps for long drives.", "excerpt": "I love Gemini in Google Maps for long drives. I start getting bored of music and podcasts and start grilling it with random questions I've always wondered about.", "context": "", "use_case": "voice Q&A while driving", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 796243056, "item_id": 49765191, "url": "https://news.ycombinator.com/item?id=49765191", "by": "rerdavies", "date": "2026-09-19", "stance": "recommend", "quote": "I use Gemini frequently, with Google Auto, and whenever I make that sort of query, which I do often, it displays \"Searching on Google Maps...\", and comes up with correct results.", "excerpt": "That is strange. I use Gemini frequently, with Google Auto, and whenever I make that sort of query, which I do often, it displays \"Searching on Google Maps...\", and comes up with correct results. Odd that the desktop version doesn't have the same functionality.", "context": "", "use_case": "location-based queries", "switched_from": "", "story": "Gemini hacked three companies in first known breakout by Google's AI"}, {"id": 795593424, "item_id": 49724589, "url": "https://news.ycombinator.com/item?id=49724589", "by": "atraac", "date": "2026-09-16", "stance": "recommend", "quote": "But other than that I actually like Gemini, I check stuff against it all the time", "excerpt": "I also had that issue happen to me, surprisingly only when I used Polish, not English. But other than that I actually like Gemini, I check stuff against it all the time, especially when walking my dog. It also works in AndroidAuto for me, but I use very basic stuff like changing Spotify music. I was on iOS before and there's no comparison to old Siri that was just garbage. I use Gemini practically every day, it's fin", "context": "Android user, previously on iOS", "use_case": "general assistant, in-car voice", "switched_from": "Siri", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}]}], "caveats": [{"label": "Coding and agents", "summary": "Several commenters say it lags for coding and agentic work.", "quotes": [{"id": 801186256, "item_id": 50074141, "url": "https://news.ycombinator.com/item?id=50074141", "by": "ralusek", "date": "2026-10-13", "stance": "recommend", "quote": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes.", "excerpt": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes. I never touch 3.8, it's awful. Curious to try this, but I've yet to use any Gemini that is good for agentic work. Also, unrelated but this made me look at Artificial Analysis to see where it lands on Cost per Task, and it ranks Opus 5.5 at almost double Astra 6. That does not align with my experience.", "context": "", "use_case": "primary chatbot", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 795512144, "item_id": 49719509, "url": "https://news.ycombinator.com/item?id=49719509", "by": "Keyframe", "date": "2026-09-15", "stance": "recommend", "quote": "I've been using gemini personally instead of what I used regular google searches for the better part.", "excerpt": "Anecdata, but I've been using gemini personally instead of what I used regular google searches for the better part. Even in car chat/search and some lighter and not so light research (if it's not heavy on technicals). It's good enough that I use it nonstop like that. I wouldn't trust it for coding at all - switching between fable and now astra. Google in a sense won (me over) like that. I also expected them to brute ", "context": "", "use_case": "search and light research", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 798700450, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "warn", "quote": "I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else.", "excerpt": "While that\u2019s true, I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else. I pay for lots of models because they\u2019re good at different things: $20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t, but I\u2019m yet to have any Gemini model find a real bug, and Gemini\u2019s results for general work will sometim", "context": "", "use_case": "data extraction", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}]}, {"label": "Hallucinations", "summary": "Users report confident misremembering, invented details and stubborn wrong answers.", "quotes": [{"id": 800484864, "item_id": 50030304, "url": "https://news.ycombinator.com/item?id=50030304", "by": "literalAardvark", "date": "2026-10-10", "stance": "warn", "quote": "Please note that Gemini has a habit of \"confident slight misremembering\".", "excerpt": "I didn't know what your example was, so I used AI in one of the best ways it can be used today: I googled \"Mel's famous chess demo\" and it blurted out this beautiful thing, which I am sharing here for discussion context: \"Mel's famous chess demo\" appears to be a slight misremembering of the legendary hacker folklore epic, The Story of Mel. In the actual story, the \"Real Programmer\" named Mel Kaye didn't code a chess ", "context": "", "use_case": "answering search queries", "switched_from": "", "story": "Programming Isn't Special"}, {"id": 799102673, "item_id": 49943917, "url": "https://news.ycombinator.com/item?id=49943917", "by": "user2722", "date": "2026-10-03", "stance": "warn", "quote": "Google's Gemini hallucinated spots or imagined details", "excerpt": "I moved from a densely populated area to a more sparse one. I'll probably renew Kagi because its assistant can answer my questions, such as: \"find me a location where I can be on my computer but also public where I can also be with a group of people\". Google's Gemini hallucinated spots or imagined details -- at one point it included a shed in the middle of a road -- the shed existed, nothing else did. DDG did similar", "context": "", "use_case": "finding locations", "switched_from": "", "story": "An Update on Orion for Linux and Windows"}, {"id": 799972512, "item_id": 49998282, "url": "https://news.ycombinator.com/item?id=49998282", "by": "svnt", "date": "2026-10-07", "stance": "warn", "quote": "It is one thing to avoid sycophancy, but Gemini often seems to go well beyond that.", "excerpt": "Gemini has been like that. One early model I used I asked it about another company\u2019s model. It insisted it didn\u2019t exist. I told it when it was released and to search. It did, and found results, but told me it wasn\u2019t really a public model and I couldn\u2019t use it. I screenshotted the pricing page. It told me I got that from somewhere else, it couldn\u2019t be correct, because it couldn\u2019t access that page. It is one thing to a", "context": "", "use_case": "", "switched_from": "", "story": "AI Model Groupthink"}]}, {"label": "Forced integration", "summary": "Some dislike Gemini being pushed into Android, Classroom and other Google products.", "quotes": [{"id": 799438256, "item_id": 49964891, "url": "https://news.ycombinator.com/item?id=49964891", "by": "76SlashDolphin", "date": "2026-10-05", "stance": "warn", "quote": "Google keeps shoving Gemini down everyone's throats", "excerpt": "Just be careful with the 8 because their motherboards tend to randomly fry themselves - both me and a friend had this happen around 2 years into owning ours and there are a decent number of people online with the same issue. Switched to the 10a on sale right before the price hike and man I'm glad I did. It'll probably be the last great Pixel if hardware costs keep getting worse and Google keeps shoving Gemini down ev", "context": "", "use_case": "", "switched_from": "", "story": "Pixel 11 doesn't yet meet the GrapheneOS security standards and may be skipped"}, {"id": 799576576, "item_id": 49973536, "url": "https://news.ycombinator.com/item?id=49973536", "by": "iamarobot", "date": "2026-10-06", "stance": "warn", "quote": "the amount of AI forced down our throats is on another level", "excerpt": "As a high schooler, the amount of AI forced down our throats is on another level. We have assignments with Claude Prose, tutors that hallucinate, and even gemini in the apps we use to access our assignments. Even my friend's brother(a 4th grader) uses AI to generate pictures for his slideshow about \"Penguins\". Education is definitely facing a turn, but is it for the worse? Link: https://workspaceupdates.googleblog.co", "context": "high school student", "use_case": "school assignments", "switched_from": "", "story": "AI tutoring with Khanmigo in a two-year school experiment"}, {"id": 796822320, "item_id": 49801395, "url": "https://news.ycombinator.com/item?id=49801395", "by": "disgruntledphd2", "date": "2026-09-22", "stance": "warn", "quote": "after the Gemini update it started refusing to set a timer for me, so I churned.", "excerpt": "> Gemini is similarly a step back. Google Assistant could hear me speak up and ask it to like or skip a song being played, driving or otherwise. It would quickly beep at me, pause the music/etc, accept input, process, then finish and resume the music (or skip to next track if asked). Yeah I used the old Assistant regularly, but after the Gemini update it started refusing to set a timer for me, so I churned.", "context": "", "use_case": "voice assistant", "switched_from": "Google Assistant", "story": "Ask HN: Is it impossible to disable Siri on macOS 27?"}]}, {"label": "App and rollout", "summary": "Some say the apps work worse than the API, and paid users report delayed access to new models.", "quotes": [{"id": 801201920, "item_id": 50075120, "url": "https://news.ycombinator.com/item?id=50075120", "by": "staticman2", "date": "2026-10-13", "stance": "warn", "quote": "the problem with the Gemini apps is the harness, not the model itself", "excerpt": "Often it seems like the problem with the Gemini apps is the harness, not the model itself. For example if I upload an image PDF it recognizes text worse than if I use the API.", "context": "", "use_case": "image PDF text recognition", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 799310656, "item_id": 49956916, "url": "https://news.ycombinator.com/item?id=49956916", "by": "nharada", "date": "2026-10-04", "stance": "warn", "quote": "Clearly this product is an afterthought", "excerpt": "I pay for Pro and the newest model I have access for is still 3.6 Flash, which was released in July. I never got access to 3.7 and still don't have 3.8. Clearly this product is an afterthought, since I've heard many people have the same models available. Can you imagine if a bunch of the people who paid for ChatGPT still only had access to 5.5, with no communications from OpenAI about it?", "context": "Pro subscriber", "use_case": "", "switched_from": "", "story": "Gemini app limiting what models free and AI Plus users can access"}, {"id": 803385680, "item_id": 50211605, "url": "https://news.ycombinator.com/item?id=50211605", "by": "joshstrange", "date": "2026-10-23", "stance": "warn", "quote": "Nope, fails twice \"Please try again\" then suggests just trash formatting.", "excerpt": "And it doesn't work if you are signed into multiple Google accounts :/ Today I wanted to fix some mixed formatting in a Google Doc. Ok, I'll use Gemini, it's right there and surely it's the best. Nope, fails twice \"Please try again\" then suggests just trash formatting. Ok, fine, I connected this to ChatGPT, let's try that. Nope, multiple rounds of \"I can't see that document\" despite having the plugin configured. Ok, ", "context": "signed into multiple Google accounts", "use_case": "fixing Google Doc formatting", "switched_from": "", "story": "Claude Now Works with Google Docs, Sheets, and Slides"}]}, {"label": "Memory wipes", "summary": "One heavy user reports repeated unannounced loss of conversation history.", "quotes": [{"id": 801555264, "item_id": 50097204, "url": "https://news.ycombinator.com/item?id=50097204", "by": "Christine725", "date": "2026-10-14", "stance": "warn", "quote": "After eight consecutive memory wipes, I mostly stopped using Gemini.", "excerpt": "Gemini\u2019s system has always been like this. I used it heavily from last September through March this year, and have been using it on and off since then \u2014 this has been the case since at least Gemini Pro 3.1. And that\u2019s not even the worst of it. When its system detects something it deems \u201cseemingly inappropriate,\u201d it just freaks out. What I\u2019ve personally experienced includes: (on the web version) wiping Gemini\u2019s previo", "context": "heavy user Sept to March", "use_case": "everyday chat", "switched_from": "", "story": "Gemini 4 Argon"}]}, {"label": "Account risk", "summary": "One commenter avoids it for fear of being locked out of their Google account.", "quotes": [{"id": 801468288, "item_id": 50091768, "url": "https://news.ycombinator.com/item?id=50091768", "by": "rdtsc", "date": "2026-10-14", "stance": "warn", "quote": "That's why I stay away from trying Gemini or doing anything much with Google", "excerpt": "That's why I stay away from trying Gemini or doing anything much with Google until I still host my main gmail account there. One misstep and I'll find myself locked out. Because it's Google's job to spy on everyone, if I have other accounts there, those will also locked out too (\"oh! you're trying to circumvent our ban? we noticed!\" kind of a thing). Then the only recourse from what I understand is to make an HN post", "context": "", "use_case": "", "switched_from": "", "story": "Google is silently linking your phone number across all signed-in accounts"}]}], "who": [{"by": "TacticalCoder", "context": "pays for an Anthropic subscription", "url": "https://news.ycombinator.com/item?id=50292239", "date": "2026-10-29"}, {"by": "bayindirh", "context": "uses LLMs as glorified search engines", "url": "https://news.ycombinator.com/item?id=50288546", "date": "2026-10-29"}, {"by": "hypendev", "context": "uses Gemini in prod via Google Cloud", "url": "https://news.ycombinator.com/item?id=50286637", "date": "2026-10-29"}, {"by": "dizhn", "context": "amateur+", "url": "https://news.ycombinator.com/item?id=50256647", "date": "2026-10-27"}, {"by": "curioustinkerer", "context": "Python backend engineer, 7+ years", "url": "https://news.ycombinator.com/item?id=49989699", "date": "2026-10-07"}, {"by": "martythemaniak", "context": "parent", "url": "https://news.ycombinator.com/item?id=49966448", "date": "2026-10-05"}, {"by": "samspot", "context": "switched to Linux last year", "url": "https://news.ycombinator.com/item?id=49923999", "date": "2026-10-01"}, {"by": "nozzlegear", "context": "used it for a month over the summer", "url": "https://news.ycombinator.com/item?id=49914768", "date": "2026-09-30"}, {"by": "fsniper", "context": "new to electronics", "url": "https://news.ycombinator.com/item?id=49740207", "date": "2026-09-17"}, {"by": "atraac", "context": "Android user, previously on iOS", "url": "https://news.ycombinator.com/item?id=49724589", "date": "2026-09-16"}, {"by": "ogogmad", "context": "pays for both", "url": "https://news.ycombinator.com/item?id=49655106", "date": "2026-09-11"}, {"by": "softwarewright", "context": "single person LLC", "url": "https://news.ycombinator.com/item?id=49591330", "date": "2026-09-06"}], "tags": ["for non-coding tasks", "for research and learning", "for OCR and data extraction", "for Android and Maps users", "for budget users"], "use_cases": ["coding", "ai assistant", "ai coding", "voice assistant", "vibe coding", "chat assistant"], "compared": [{"slug": "claude", "name": "Claude", "co": 146, "switched_from": 3, "switched_to": 1}, {"slug": "chatgpt", "name": "ChatGPT", "co": 99, "switched_from": 10, "switched_to": 5}, {"slug": "codex", "name": "Codex", "co": 52, "switched_from": 0, "switched_to": 2}, {"slug": "claude-code", "name": "Claude Code", "co": 44, "switched_from": 0, "switched_to": 1}, {"slug": "claude-opus", "name": "Claude Opus", "co": 42, "switched_from": 0, "switched_to": 1}, {"slug": "gpt-5", "name": "GPT-5", "co": 24, "switched_from": 1, "switched_to": 0}, {"slug": "grok", "name": "Grok", "co": 26, "switched_from": 0, "switched_to": 0}, {"slug": "claude-sonnet", "name": "Claude Sonnet", "co": 23, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49715947", "title": "Gemini 3.8 Live and 3.8 Live Extended Thinking", "mentions": 10}, {"url": "https://news.ycombinator.com/item?id=49537553", "title": "Gemini 3.8 Flash and 3.8 Flash Cyber", "mentions": 9}, {"url": "https://news.ycombinator.com/item?id=50073879", "title": "Gemini 4 Argon", "mentions": 7}, {"url": "https://news.ycombinator.com/item?id=49289112", "title": "Gemini 3.7 Flash", "mentions": 7}, {"url": "https://news.ycombinator.com/item?id=49672966", "title": "Ask HN: What default model do you use and why?", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=48993414", "title": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber", "mentions": 6}], "sentiment_by_month": {"2025-11": {"neutral": 9, "warn": 7, "recommend": 13, "compare": 1}, "2025-12": {"warn": 8, "recommend": 16, "neutral": 6, "compare": 1}, "2026-01": {"warn": 7, "neutral": 14, "recommend": 14, "compare": 4}, "2026-02": {"recommend": 14, "neutral": 14, "warn": 7, "compare": 2}, "2026-03": {"neutral": 8, "recommend": 6, "warn": 3, "compare": 7}, "2026-04": {"recommend": 6, "neutral": 6, "compare": 2, "warn": 3}, "2026-05": {"warn": 6, "neutral": 8, "recommend": 5, "compare": 1}, "2026-06": {"recommend": 21, "warn": 15, "neutral": 22, "compare": 1}, "2026-07": {"recommend": 18, "neutral": 13, "warn": 12}, "2026-08": {"neutral": 25, "recommend": 18, "warn": 11, "compare": 2}, "2026-09": {"recommend": 31, "neutral": 17, "warn": 9, "compare": 7}, "2026-10": {"warn": 15, "neutral": 14, "recommend": 18, "compare": 1}}, "quotes": [{"id": 805104882, "item_id": 50319055, "url": "https://news.ycombinator.com/item?id=50319055", "by": "jtangelder", "date": "2026-10-31", "stance": "neutral", "quote": "Further debugging of the protocol was done in collaboration with Gemini", "excerpt": "I created ReFUSE to bring my old Fender Mustang (from 2013) modelling amplifier back to life. The amplifier itself still sounds great, especially for home practise, but the official Fender FUSE control software was discontinued years ago. The software let you configure the amp models and effects, their parameters etc, which aren't not accessible from the physical knobs on the amplifier itself. And because it was orig", "context": "", "use_case": "protocol reverse engineering", "switched_from": "", "story": "Control legacy Fender Mustang amps from the browser via WebHID"}, {"id": 805102448, "item_id": 50318903, "url": "https://news.ycombinator.com/item?id=50318903", "by": "cshutchinson", "date": "2026-10-31", "stance": "neutral", "quote": "Yes I used the tool Gemini to write my review of Gemini Code", "excerpt": "My apologies for the excessive restriction on my link. Fixed. Yes I used the tool Gemini to write my review of Gemini Code as it would add some degree of impartiality on its own behalf. I wrote this comment myself so it will check as real and not AI for everyone.", "context": "", "use_case": "writing a review", "switched_from": "", "story": "Gemini Code vs. Claude Code \u2013 A cautionary post-mortem ($800 in 12h)"}, {"id": 804807794, "item_id": 50300487, "url": "https://news.ycombinator.com/item?id=50300487", "by": "ashdksnndck", "date": "2026-10-30", "stance": "neutral", "quote": "I\u2019m a $20/paid user for both Gemini and Claude.", "excerpt": "If I have a really straightforward question and I want a fast answer I\u2019ll sometimes Google search for the AI overview. But it\u2019s so unreliable. I use opus 5.5 for any question that Google could plausibly screw up. This is a huge product failure on Google\u2019s part, IMO. I\u2019m a $20/paid user for both Gemini and Claude. It\u2019s nuts that with Google\u2019s massive head-start in AI (and apparently they still are capable of making a ", "context": "", "use_case": "AI assistant", "switched_from": "", "story": "Google Search is now less than half of Alphabet\u2019s revenue"}, {"id": 804688019, "item_id": 50293001, "url": "https://news.ycombinator.com/item?id=50293001", "by": "novaRom", "date": "2026-10-29", "stance": "compare", "quote": "it was best choice for daily usage. Nice, clear answers, never nonsense.", "excerpt": "I have switched to Mistral free app just from US apps completely recently - it beats for me absolutely all alternatives: ChatGPT - stopped using it like a year ago, it feels they deliberately made it ridiculously stupid (for fun?). I know, they were first, but today it's a joke. Claude - tried it out of curiosity few times, but it's close to nothing when it's about non coding questions. I don't understand how anyone ", "context": "based in EU", "use_case": "daily chat assistant", "switched_from": "ChatGPT", "story": "We're releasing the weights of Mistral Large 4"}, {"id": 804675825, "item_id": 50292239, "url": "https://news.ycombinator.com/item?id=50292239", "by": "TacticalCoder", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini is also IMO excellent for everything that is not coding.", "excerpt": "Not a moat and not big but... for SMEs \"Google Workspace\" is a godsend from outter space. This is what allow little SMEs to not have to suffer that piece of shit that Windows is. I know people running their SMEs (and I helped them set up Google Workspace) from Mac and Chromebooks since years and years and who do not ever want to here again from anything Microsoft. They're basically doing everything inside \"Google Wor", "context": "pays for an Anthropic subscription", "use_case": "non-coding tasks", "switched_from": "", "story": "Google Search is now less than half of Alphabet\u2019s revenue"}, {"id": 804621056, "item_id": 50288816, "url": "https://news.ycombinator.com/item?id=50288816", "by": "sgc", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini has and does absolutely dominate for this.", "excerpt": "For ocr, you have to practice, practice, practice with your prompts on small sample sizes before one-shotting a book. I create a json schema for the output that describes the structure in detail (using ai from my prose descriptions of structure of course). I have specific tough pages I use on openrouter to test every new model I am interested in. Gemini has and does absolutely dominate for this. But flash can be bett", "context": "", "use_case": "OCR of books", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 804616736, "item_id": 50288546, "url": "https://news.ycombinator.com/item?id=50288546", "by": "bayindirh", "date": "2026-10-29", "stance": "recommend", "quote": "I find myself using it more than Claude.", "excerpt": "People always love to think the AI race is a duopoly (OpenAI vs. Anthropic), but from what I have experienced, Gemini was always holding on its own, and I find myself using it more than Claude. True, I use LLMs as glorified search engines to unearth material to read myself, but Gemini is much more useful if you decide to learn yourself. It also offers interesting expansions to your questions. While I don't offload my", "context": "uses LLMs as glorified search engines", "use_case": "research and learning", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 804603792, "item_id": 50287737, "url": "https://news.ycombinator.com/item?id=50287737", "by": "xrd", "date": "2026-10-29", "stance": "neutral", "quote": "my little pocket friend (an AI called Gemini, perhaps you know him?)", "excerpt": "I keep searching for Brother printers at Goodwill because apparently they are the best for non-DRM cartridges. But, when I use my little pocket friend (an AI called Gemini, perhaps you know him?) he often indicates that the printer I'm seeing is 12 years old, and probably has wear and tear on the rollers. Does anyone know if this is true? I would really like to get a printer that avoids the cartridge cartels. But, Go", "context": "", "use_case": "checking used printer condition", "switched_from": "", "story": "Getting debug access on a Brother printer over Telnet"}, {"id": 804586192, "item_id": 50286637, "url": "https://news.ycombinator.com/item?id=50286637", "by": "hypendev", "date": "2026-10-29", "stance": "recommend", "quote": "I use their models and for my niche they are the best for good quality at great speeds.", "excerpt": "I was confused a bit where this was. Then I had to Google Gemini, which lead me to gemini.google.com (did not know it existed, and I use gemini in prod via google cloud). First thing there that got me was that all of my Google searches. Why? I googled \"snoop dog real name\". Why is this considered a gemini chat now? If I actually used it, my chats would be buried under dumb quick google searches I did. And it seems it", "context": "uses Gemini in prod via Google Cloud", "use_case": "production app via API", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 804566800, "item_id": 50285425, "url": "https://news.ycombinator.com/item?id=50285425", "by": "spockz", "date": "2026-10-29", "stance": "recommend", "quote": "3.8 medium is my daily driver. This gets me pretty far.", "excerpt": "I\u2019m using the default anti gravity setup. 3.8 medium is my daily driver. This gets me pretty far. (Definitely not as far as Luna and Sol). When I ask the same question to Argon it is 50% of my weekly usage limit gone. So either the usage limit is really a lot smaller or somehow argon thinks a whole lot more even for simple tasks.", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 804530960, "item_id": 50283185, "url": "https://news.ycombinator.com/item?id=50283185", "by": "layman51", "date": "2026-10-29", "stance": "neutral", "quote": "When I use the Gemini app for iOS, it says that I\u2019m on \u201cUltra\u201d in the left sidebar near the bottom.", "excerpt": "Same here. When I use the Gemini app for iOS, it says that I\u2019m on \u201cUltra\u201d in the left sidebar near the bottom. It doesn\u2019t say that when I\u2019m using Gemini on the web.", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 804518465, "item_id": 50282404, "url": "https://news.ycombinator.com/item?id=50282404", "by": "armcat", "date": "2026-10-28", "stance": "neutral", "quote": "I used Google Search with Gemini summaries and got the same answer.", "excerpt": "I asked ChatGPT and it answered Joe Biden. I used Google Search with Gemini summaries and got the same answer. Regarding Google is it geo dependent? Like Lake Ontario?", "context": "", "use_case": "factual question", "switched_from": "", "story": "Google AI Search Refuses to Say Who Won the 2020 Election"}, {"id": 804227105, "item_id": 50264194, "url": "https://news.ycombinator.com/item?id=50264194", "by": "kazinator", "date": "2026-10-27", "stance": "recommend", "quote": "I gave it some real problems for which I used Gemini.", "excerpt": "I just played with Nova after seeing this submission. I gave it some real problems for which I used Gemini. It markedly \"dumb\" in comparison, losing sight of facts that I presented in the first prompt of the chat, and other subsequently introduced, and its responses contain repetitions of the same point-form advice. It's like GPT-3 level or something.", "context": "", "use_case": "", "switched_from": "", "story": "Amazon Is Gutting Its AI Division After Sustained Failure"}, {"id": 804106353, "item_id": 50256647, "url": "https://news.ycombinator.com/item?id=50256647", "by": "dizhn", "date": "2026-10-27", "stance": "recommend", "quote": "Gemini models are actually fine for me as an amateur+", "excerpt": "I tried the Claude $20 plan for two weeks and burned the rest of it due to how much token anxiety it gave me. And I'm not ready to keep throwing money at it for it to become usable. Gemini models are actually fine for me as an amateur+ I found especially since they have regional pricing and a very generous side items package. I use the models but not the \"harness\" though. Not directly anyway. I am still handicapped b", "context": "amateur+", "use_case": "coding models", "switched_from": "Claude", "story": "Anthropic S-1"}, {"id": 803909682, "item_id": 50244355, "url": "https://news.ycombinator.com/item?id=50244355", "by": "mathewjacob", "date": "2026-10-26", "stance": "recommend", "quote": "Gemini web which had the best OCR + context window combo at the time", "excerpt": "I've built what I believe is currently the best free, online resource for learning Malayalam from scratch. It is based on a textbook and related materials made available by the University of Texas at Austin (UT) which are available under the Creative Commons License. It is a full University course with grammar lessons, vocabulary, and audio clips. I've used those to also build Anki decks for flash cards. A significan", "context": "", "use_case": "OCR of textbook", "switched_from": "", "story": "Malayalam: A University Course"}, {"id": 803722976, "item_id": 50232686, "url": "https://news.ycombinator.com/item?id=50232686", "by": "Avamander", "date": "2026-10-25", "stance": "recommend", "quote": "I recommend comparing what it rewrites to something that Gemini models output.", "excerpt": "I recommend comparing what it rewrites to something that Gemini models output. I think there's still a lot that Anthropic could improve.", "context": "", "use_case": "rewriting text style", "switched_from": "", "story": "Listen and read USA nuclear forces Emergency Action Messages, heard on 11175 kHz"}, {"id": 803385680, "item_id": 50211605, "url": "https://news.ycombinator.com/item?id=50211605", "by": "joshstrange", "date": "2026-10-23", "stance": "warn", "quote": "Nope, fails twice \"Please try again\" then suggests just trash formatting.", "excerpt": "And it doesn't work if you are signed into multiple Google accounts :/ Today I wanted to fix some mixed formatting in a Google Doc. Ok, I'll use Gemini, it's right there and surely it's the best. Nope, fails twice \"Please try again\" then suggests just trash formatting. Ok, fine, I connected this to ChatGPT, let's try that. Nope, multiple rounds of \"I can't see that document\" despite having the plugin configured. Ok, ", "context": "signed into multiple Google accounts", "use_case": "fixing Google Doc formatting", "switched_from": "", "story": "Claude Now Works with Google Docs, Sheets, and Slides"}, {"id": 803029713, "item_id": 50189357, "url": "https://news.ycombinator.com/item?id=50189357", "by": "jacquesm", "date": "2026-10-22", "stance": "warn", "quote": "I haven't used it as much because it was performing quite poor for what I was doing", "excerpt": "No. I've had pretty much every model I've worked with (list too long to recite) spit out the odd Chinese, Korean, Thai or other Asian chunk of letters from time to time. ChatGPT in various incarnations has suddenly switched to Chinese in mid-output and remained that way until told to switch back. The only one I haven't really seen this from as far as I can recall is Gemini, but then again, I haven't used it as much b", "context": "", "use_case": "", "switched_from": "", "story": "Mistral Large 4"}, {"id": 802906768, "item_id": 50181673, "url": "https://news.ycombinator.com/item?id=50181673", "by": "sirenic", "date": "2026-10-21", "stance": "neutral", "quote": "I use Gemini within the Gmail suite", "excerpt": "I use Gemini within the Gmail suite, and this happens without the knowledge of the people who send me emails... What solutions might be available to anonymize data sources?", "context": "", "use_case": "AI in email", "switched_from": "", "story": "Show HN: WhatsApp MCP running free on Cloudflare"}, {"id": 801844658, "item_id": 50115291, "url": "https://news.ycombinator.com/item?id=50115291", "by": "zdp7", "date": "2026-10-16", "stance": "neutral", "quote": "I had been using Gemini to build OpenScad models.", "excerpt": "I had been using Gemini to build OpenScad models. The other day Gemini mentioned CadQuery as an option. It's essentially OpenScad for Python. The big plus is b-rep modeler. https://github.com/cadquery/cadquery", "context": "", "use_case": "generating CAD models", "switched_from": "", "story": "Ask HN: CAD for wood working with LLM support?"}, {"id": 801820736, "item_id": 50113796, "url": "https://news.ycombinator.com/item?id=50113796", "by": "verdverm", "date": "2026-10-16", "stance": "recommend", "quote": "if you use mostly flash models, it goes on forever", "excerpt": "if you use mostly flash models, it goes on forever either way, the quotas are very generous, my usage pattern gets me around 250M tokens on the $10 plan, 1B on the $40 plan where I used more Kimi k3", "context": "", "use_case": "high-volume token usage", "switched_from": "", "story": "Ask HN: Thoughts about the Gemini Web app?"}, {"id": 801806112, "item_id": 50112882, "url": "https://news.ycombinator.com/item?id=50112882", "by": "bahmboo", "date": "2026-10-16", "stance": "neutral", "quote": "gemini says I can get it to repower itself.", "excerpt": "How do they do with staying on and then restarting everything after power off? Can they automatically repower? I don't have my embedded macbook fully configured but gemini says I can get it to repower itself. By repower I mean if the power goes out and then returns the machine needs to power on and boot. I have a couple of older Chromebooks I use in rando locations (basement, shop, car, rv, boat etc). And they are gr", "context": "", "use_case": "asking setup questions", "switched_from": "", "story": "What I self-host"}, {"id": 801555264, "item_id": 50097204, "url": "https://news.ycombinator.com/item?id=50097204", "by": "Christine725", "date": "2026-10-14", "stance": "warn", "quote": "After eight consecutive memory wipes, I mostly stopped using Gemini.", "excerpt": "Gemini\u2019s system has always been like this. I used it heavily from last September through March this year, and have been using it on and off since then \u2014 this has been the case since at least Gemini Pro 3.1. And that\u2019s not even the worst of it. When its system detects something it deems \u201cseemingly inappropriate,\u201d it just freaks out. What I\u2019ve personally experienced includes: (on the web version) wiping Gemini\u2019s previo", "context": "heavy user Sept to March", "use_case": "everyday chat", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801468288, "item_id": 50091768, "url": "https://news.ycombinator.com/item?id=50091768", "by": "rdtsc", "date": "2026-10-14", "stance": "warn", "quote": "That's why I stay away from trying Gemini or doing anything much with Google", "excerpt": "That's why I stay away from trying Gemini or doing anything much with Google until I still host my main gmail account there. One misstep and I'll find myself locked out. Because it's Google's job to spy on everyone, if I have other accounts there, those will also locked out too (\"oh! you're trying to circumvent our ban? we noticed!\" kind of a thing). Then the only recourse from what I understand is to make an HN post", "context": "", "use_case": "", "switched_from": "", "story": "Google is silently linking your phone number across all signed-in accounts"}, {"id": 801353968, "item_id": 50084623, "url": "https://news.ycombinator.com/item?id=50084623", "by": "jakderrida", "date": "2026-10-14", "stance": "recommend", "quote": "you can plug it into any gemini and have it transcribe and diarize the video.", "excerpt": "If a video is less than 45 minutes, you can plug it into any gemini and have it transcribe and diarize the video. (although, I've been told it only works on aistudio anymore) Sometimes it trips up. However, plugging in videos longer than 45 minutes quickly leads to ludicrous behavior the longer it is over 45 minutes. You can even just plug in the Youtube link with a short prompt. Bear in mind that thinking that plugg", "context": "", "use_case": "video transcription and diarization", "switched_from": "", "story": "Show HN: I built a tool to track what AI leaders say and how their views change"}, {"id": 801324832, "item_id": 50082802, "url": "https://news.ycombinator.com/item?id=50082802", "by": "casey2", "date": "2026-10-14", "stance": "neutral", "quote": "I used to use gemini til google banned my 20+ year email for \"bot-like behavior\".", "excerpt": "Mindboggling output window. I'm kinda jealous, I used to use gemini til google banned my 20+ year email for \"bot-like behavior\". Still reading up on it here: https://ai.google.dev/gemini-api/docs/long-decode and needs lots of community testing to determine whether it's a \"true\" 1M token output window.", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801299201, "item_id": 50081200, "url": "https://news.ycombinator.com/item?id=50081200", "by": "astlouis44", "date": "2026-10-14", "stance": "neutral", "quote": "Just gemini as antigravity requires Ultra subscription to use it in that IDE", "excerpt": "Just gemini as antigravity requires Ultra subscription to use it in that IDE, whereas Argon is/was available for me on web, so I used the latter", "context": "", "use_case": "web chat generation", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801236976, "item_id": 50077311, "url": "https://news.ycombinator.com/item?id=50077311", "by": "jeffrallen", "date": "2026-10-13", "stance": "recommend", "quote": "I use Gemini all day at work via the chat interface. It's rock solid.", "excerpt": "I use Gemini all day at work via the chat interface. It's rock solid. I find it hard to understand which model it's using though. Am I already using Argon, or does it switch models according to the subject?", "context": "", "use_case": "work chat assistant", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801201920, "item_id": 50075120, "url": "https://news.ycombinator.com/item?id=50075120", "by": "staticman2", "date": "2026-10-13", "stance": "warn", "quote": "the problem with the Gemini apps is the harness, not the model itself", "excerpt": "Often it seems like the problem with the Gemini apps is the harness, not the model itself. For example if I upload an image PDF it recognizes text worse than if I use the API.", "context": "", "use_case": "image PDF text recognition", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801186256, "item_id": 50074141, "url": "https://news.ycombinator.com/item?id=50074141", "by": "ralusek", "date": "2026-10-13", "stance": "recommend", "quote": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes.", "excerpt": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes. I never touch 3.8, it's awful. Curious to try this, but I've yet to use any Gemini that is good for agentic work. Also, unrelated but this made me look at Artificial Analysis to see where it lands on Cost per Task, and it ranks Opus 5.5 at almost double Astra 6. That does not align with my experience.", "context": "", "use_case": "primary chatbot", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801186257, "item_id": 50074141, "url": "https://news.ycombinator.com/item?id=50074141", "by": "ralusek", "date": "2026-10-13", "stance": "warn", "quote": "I never touch 3.8, it's awful.", "excerpt": "3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes. I never touch 3.8, it's awful. Curious to try this, but I've yet to use any Gemini that is good for agentic work. Also, unrelated but this made me look at Artificial Analysis to see where it lands on Cost per Task, and it ranks Opus 5.5 at almost double Astra 6. That does not align with my experience.", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801177137, "item_id": 50073571, "url": "https://news.ycombinator.com/item?id=50073571", "by": "tkdb", "date": "2026-10-13", "stance": "warn", "quote": "Gemini, for a consumer of the google ecosystem, is also maddeningly, bafflingly worthless.", "excerpt": "Nice very Apple-esque thrust to unify and refine a chaotic field of tech into an elegant experience. I cannot fathom how this will deliver on the vision when Siri, even the new gemini-under-the-hood Siri, is still maddeningly, bafflingly worthless. To be fair, Gemini, for a consumer of the google ecosystem, is also maddeningly, bafflingly worthless. So we use ChatGPT or Claude, with extremely limited access to the ti", "context": "consumer of the Google ecosystem", "use_case": "", "switched_from": "", "story": "Apple HomeView"}, {"id": 800484864, "item_id": 50030304, "url": "https://news.ycombinator.com/item?id=50030304", "by": "literalAardvark", "date": "2026-10-10", "stance": "warn", "quote": "Please note that Gemini has a habit of \"confident slight misremembering\".", "excerpt": "I didn't know what your example was, so I used AI in one of the best ways it can be used today: I googled \"Mel's famous chess demo\" and it blurted out this beautiful thing, which I am sharing here for discussion context: \"Mel's famous chess demo\" appears to be a slight misremembering of the legendary hacker folklore epic, The Story of Mel. In the actual story, the \"Real Programmer\" named Mel Kaye didn't code a chess ", "context": "", "use_case": "answering search queries", "switched_from": "", "story": "Programming Isn't Special"}, {"id": 800422784, "item_id": 50026424, "url": "https://news.ycombinator.com/item?id=50026424", "by": "ButlerianJihad", "date": "2026-10-09", "stance": "recommend", "quote": "Gemini is really good about surfacing summaries and overviews and answering thorny questions", "excerpt": "I found the consumer facing \"tax professionals\" to be indifferent and apparently, nearly incompetent. Like, I walked into a tax office in my neighborhood and the certified dude could not answer a question without typing it into the Search Box on his computer. In contrast, I found Gemini to be pretty good at directing me to verify my own answers at IRS.gov. It was able to answer correctly but of course, Gemini is not ", "context": "", "use_case": "tax questions", "switched_from": "", "story": "Ask HN: Why hasn't AI replaced Tax filing software"}, {"id": 800403127, "item_id": 50025195, "url": "https://news.ycombinator.com/item?id=50025195", "by": "aftbit", "date": "2026-10-09", "stance": "warn", "quote": "I've had middling success with models like DS V4.1 Flash and free Gemini.", "excerpt": "I have had good luck rotating between the three tiers of GPT 5.6 with occasional jumps up to Astra or Fable. Most of my work is with GPT-5.6-Sol. Simple tasks like data extraction or trivial refactors (rename this variable etc) I often push down to Terra or Luna, or even to self-hosted Gemma4:31B. Very tricky stuff, like planning a new feature, design review, or code review of a complex change across multiple reposit", "context": "", "use_case": "easy coding tasks", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800292912, "item_id": 50018307, "url": "https://news.ycombinator.com/item?id=50018307", "by": "tacomagick", "date": "2026-10-09", "stance": "neutral", "quote": "My organization provides free Gemini access", "excerpt": "My organization provides free Gemini access, I use Deepseek myself. I have a Opencode Go subscription for the time being because it provides both ZDR with their agreement with Deepseek and 10$ of subscription turns to 60$ of credits for Deepseek as part of their release discount.", "context": "", "use_case": "work AI assistant", "switched_from": "", "story": "Ask HN: Are you a subscribed LLM or a locally deployed open-source model?"}, {"id": 800091872, "item_id": 50005742, "url": "https://news.ycombinator.com/item?id=50005742", "by": "HelloMcFly", "date": "2026-10-08", "stance": "recommend", "quote": "I use Gemini more than any other model at the moment", "excerpt": "I use Gemini more than any other model at the moment, I have absolutely no idea what you're talking about with this experience.", "context": "", "use_case": "", "switched_from": "", "story": "GPT\u20116 and Intelligent UI for everyone"}, {"id": 799972512, "item_id": 49998282, "url": "https://news.ycombinator.com/item?id=49998282", "by": "svnt", "date": "2026-10-07", "stance": "warn", "quote": "It is one thing to avoid sycophancy, but Gemini often seems to go well beyond that.", "excerpt": "Gemini has been like that. One early model I used I asked it about another company\u2019s model. It insisted it didn\u2019t exist. I told it when it was released and to search. It did, and found results, but told me it wasn\u2019t really a public model and I couldn\u2019t use it. I screenshotted the pricing page. It told me I got that from somewhere else, it couldn\u2019t be correct, because it couldn\u2019t access that page. It is one thing to a", "context": "", "use_case": "", "switched_from": "", "story": "AI Model Groupthink"}, {"id": 799835188, "item_id": 49989699, "url": "https://news.ycombinator.com/item?id=49989699", "by": "curioustinkerer", "date": "2026-10-07", "stance": "neutral", "quote": "Gemini video understanding as a developer API", "excerpt": "Location: Lucknow, India Remote: Yes Willing to relocate: No Technologies: Python, Django, FastAPI, PostgreSQL, Celery, LLM APIs (Gemini, Claude), agentic workflows, embeddings/clustering, GCP, Terraform R\u00e9sum\u00e9/CV: https://drive.google.com/file/d/1pulNpC8VJnV01pCzg0QRhgqOTazTWhk7/view Email: 5ifocyqgf@relay.firefox.com GitHub: https://github.com/abhiabhi94 Python backend engineer, 7+ years. Lately building LLM system", "context": "Python backend engineer, 7+ years", "use_case": "video understanding API", "switched_from": "", "story": "Ask HN: Who wants to be hired? (October 2026)"}, {"id": 799576576, "item_id": 49973536, "url": "https://news.ycombinator.com/item?id=49973536", "by": "iamarobot", "date": "2026-10-06", "stance": "warn", "quote": "the amount of AI forced down our throats is on another level", "excerpt": "As a high schooler, the amount of AI forced down our throats is on another level. We have assignments with Claude Prose, tutors that hallucinate, and even gemini in the apps we use to access our assignments. Even my friend's brother(a 4th grader) uses AI to generate pictures for his slideshow about \"Penguins\". Education is definitely facing a turn, but is it for the worse? Link: https://workspaceupdates.googleblog.co", "context": "high school student", "use_case": "school assignments", "switched_from": "", "story": "AI tutoring with Khanmigo in a two-year school experiment"}, {"id": 799102673, "item_id": 49943917, "url": "https://news.ycombinator.com/item?id=49943917", "by": "user2722", "date": "2026-10-03", "stance": "warn", "quote": "Google's Gemini hallucinated spots or imagined details", "excerpt": "I moved from a densely populated area to a more sparse one. I'll probably renew Kagi because its assistant can answer my questions, such as: \"find me a location where I can be on my computer but also public where I can also be with a group of people\". Google's Gemini hallucinated spots or imagined details -- at one point it included a shed in the middle of a road -- the shed existed, nothing else did. DDG did similar", "context": "", "use_case": "finding locations", "switched_from": "", "story": "An Update on Orion for Linux and Windows"}, {"id": 798700450, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "warn", "quote": "I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else.", "excerpt": "While that\u2019s true, I have found Gemini models to be exclusively good for data extraction, and absolutely terrible at everything else. I pay for lots of models because they\u2019re good at different things: $20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t, but I\u2019m yet to have any Gemini model find a real bug, and Gemini\u2019s results for general work will sometim", "context": "", "use_case": "data extraction", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}, {"id": 797938192, "item_id": 49871137, "url": "https://news.ycombinator.com/item?id=49871137", "by": "hnbad", "date": "2026-09-27", "stance": "warn", "quote": "Literally every experience I've had with Gemini / Google Search AI answers followed this exact pattern", "excerpt": "Literally every experience I've had with Gemini / Google Search AI answers followed this exact pattern, often repeated several times more if I remained persistent instead of just giving up. Typical example: \"Where can I buy <thing I'm looking for that I can't find anywhere using normal search terms>?\" > You're looking for <related but different and widely available thing>. It is sold by <sites I never heard of>. \"No,", "context": "", "use_case": "product search", "switched_from": "", "story": "When did Google get so weird?"}, {"id": 797690595, "item_id": 49855662, "url": "https://news.ycombinator.com/item?id=49855662", "by": "assimpleaspossi", "date": "2026-09-26", "stance": "warn", "quote": "The code they supplied to me has NEVER worked or was so convoluted that I threw it away and did it myself.", "excerpt": "I find it strange to see people writing articles like this as if everyone has used AI for decades. I've programmed for decades. I thought I retired three years ago but got an offer I couldn't refuse. Already there were little things I'd forgotten how to use. Over the past six months I tried using Claude, chatgpt, Grok and Gemini. At best I got reminders of how things worked. People online say they use them to write t", "context": "", "use_case": "coding help", "switched_from": "", "story": "One Month Without AI"}, {"id": 795588320, "item_id": 49724270, "url": "https://news.ycombinator.com/item?id=49724270", "by": "paride5745", "date": "2026-09-16", "stance": "recommend", "quote": "I use gemini for everything not-coding", "excerpt": "Same here. I use gemini for everything not-coding, from doing research, to have custom personas for more niche topics (and feeding more detailed knowledge in these cases). For coding and image editing, right now I find ChatGPT superior. And for software architecture designs or planning Claude is the best since a while. I still have to try Grok to be fair.", "context": "", "use_case": "research, personas, non-coding tasks", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 795512144, "item_id": 49719509, "url": "https://news.ycombinator.com/item?id=49719509", "by": "Keyframe", "date": "2026-09-15", "stance": "recommend", "quote": "I've been using gemini personally instead of what I used regular google searches for the better part.", "excerpt": "Anecdata, but I've been using gemini personally instead of what I used regular google searches for the better part. Even in car chat/search and some lighter and not so light research (if it's not heavy on technicals). It's good enough that I use it nonstop like that. I wouldn't trust it for coding at all - switching between fable and now astra. Google in a sense won (me over) like that. I also expected them to brute ", "context": "", "use_case": "search and light research", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 795476432, "item_id": 49717277, "url": "https://news.ycombinator.com/item?id=49717277", "by": "mvdtnz", "date": "2026-09-15", "stance": "recommend", "quote": "it's my go-to for just searching basic information (replacing google search) because it's so darn fast", "excerpt": "My Gemini app is still stuck at 3.5 Flash-lite and 3.6 Flash so I truly don't understand how Google rolls this stuff out. I don't use Gemini for anything serious so I'm not going to use the API, but it's my go-to for just searching basic information (replacing google search) because it's so darn fast.", "context": "", "use_case": "quick information search", "switched_from": "Google Search", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 794784401, "item_id": 49674025, "url": "https://news.ycombinator.com/item?id=49674025", "by": "george_stephen", "date": "2026-09-12", "stance": "recommend", "quote": "Gemini for academic work to encyclopedia and know-how discussions", "excerpt": "I use all of em, ChatGPT 5.6luna ion web, for quick tasks(without signup), (ii personally feel ChatGPT isn't straightforward especially when quizing its opinion on a topic) , Gemini for academic work to encyclopedia and know-how discussions, recommending solutions to technical tasks by looking up web for me(it's my primary driver, but lags behind in coding abilities,its large context is a plus. I recently started ret", "context": "", "use_case": "academic work and research", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}]}