{"slug": "glm", "name": "GLM", "category": "ai", "category_name": "AI models and assistants", "description": "Open-weights large language model family from Z.ai, with full and Flash variants.", "recommenders": 159, "commenters": 247, "warners": 19, "score": 136.11, "rising": 28.96, "first": "2025-11-01", "latest": "2026-10-30", "why": "Liked as an open-weights alternative to frontier models that is good enough for most daily coding work, with low costs and good bug-finding and review ability.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 177, "neutral": 76, "compare": 30, "warn": 20}, "spark": [5, 4, 6, 0, 2, 8, 5, 44, 36, 25, 19, 23], "listed": true, "loved": ["Frontier alternative", "Code review"], "caveat": "Claude-like prose", "short_quote": "I've been using GLM 5.3 for the past week, and I find to does a straight up better job than Opus 5 on my projects.", "icon": false, "domain": "z.ai", "github_repo": null, "official_url": "https://z.ai", "pricing": "open source", "aliases": ["GLM", "GLM 5.2", "GLM 5.3", "GLM-5.2", "GLM 5.1", "GLM-5.3", "GLM-5.1", "GLM 4.6", "GLM 4.7", "GLM-5", "GLM-4.7", "GLM-4.6", "GLM 5.x", "GLM5.2", "GLM5.3", "GLM 5"], "verdict": [{"text": "Liked as an open-weights alternative to frontier models that is good enough for most daily coding work,", "cites": [{"id": 803899729, "item_id": 50243733, "url": "https://news.ycombinator.com/item?id=50243733", "by": "Sphax", "date": "2026-10-26", "stance": "recommend", "quote": "These chinese models are simply good enough for the vast majority of tasks I run", "excerpt": "I use Opus 5.5 daily at work and a mix of GLM 5.3 (Flash or not), Deepseek v4 (flash or pro) at home and while Opus 5.5 is more capable, in my opinion it matters for less than 5% of the work i do. These chinese models are simply good enough for the vast majority of tasks I run and when they're not I use Astra or Opus 5.5. Yes, leaving Opus 5.5 on all the time is comfortable when you pay the 90\u20ac plan but it's just not", "context": "", "use_case": "home use", "switched_from": "", "story": "Anthropic S-1"}, {"id": 790874144, "item_id": 49429634, "url": "https://news.ycombinator.com/item?id=49429634", "by": "petesergeant", "date": "2026-08-25", "stance": "recommend", "quote": "I switch to GLM5.3, and it's not quite there, but it's good enough for productive work.", "excerpt": "Someone else having been too early on a prediction has little bearing on my prediction. A year ago almost nobody was using open models as daily drivers, today they are. When I run out of Fable and Sol credits in a week, I switch to GLM5.3, and it's not quite there, but it's good enough for productive work.", "context": "", "use_case": "coding fallback", "switched_from": "", "story": "Ox-Alpha Is GLM?"}, {"id": 791254881, "item_id": 49453430, "url": "https://news.ycombinator.com/item?id=49453430", "by": "Sphax", "date": "2026-08-26", "stance": "recommend", "quote": "It definitely can be a daily driver if you don\u2019t want to use Anthropic or OpenAI.", "excerpt": "Both can be true though. I had the max coding plan since january and I kept using with Pi since then, even though it wasn\u2019t as good as opus until glm 5.3. It definitely can be a daily driver if you don\u2019t want to use Anthropic or OpenAI. It\u2019s going to be even better with native vision now available. And i\u2019m not messing with my setup either.", "context": "", "use_case": "daily coding driver", "switched_from": "", "story": "GLM-5.3-Flash"}, {"id": 794800337, "item_id": 49675021, "url": "https://news.ycombinator.com/item?id=49675021", "by": "abalashov", "date": "2026-09-12", "stance": "recommend", "quote": "Allow me to recommend switching to Kimi K3 / GLM 5.3 / DeepSeek.", "excerpt": "Allow me to recommend switching to Kimi K3 / GLM 5.3 / DeepSeek. I use all three for the better part of a year now (DeepSeek via the Reasonix harness) and haven't touched Claude Code in at least as long.", "context": "", "use_case": "coding", "switched_from": "Claude Code", "story": "We must pace the frontier"}]}, {"text": " with low costs and good bug-finding and review ability.", "cites": [{"id": 800362641, "item_id": 50022665, "url": "https://news.ycombinator.com/item?id=50022665", "by": "cco", "date": "2026-10-09", "stance": "recommend", "quote": "It is basically free, half a cent per turn maybe", "excerpt": "Yeah maybe I'll play around with different precision, I did see improvement when I went from fp4 to full fidelity though. This is my setup for Home Assistant voice, parakeet for STT, GLM 5.3 to generate responses, and Kokoro for TTS. I use local routing for simple commands like turn on the lights, but if I want to ask questions or something, it gets routed to GLM 5.3. It is basically free, half a cent per turn maybe,", "context": "", "use_case": "voice assistant responses", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 797804800, "item_id": 49862800, "url": "https://news.ycombinator.com/item?id=49862800", "by": "laoxingAI", "date": "2026-09-27", "stance": "recommend", "quote": "because the quota is so large, it feels really great to use", "excerpt": "GLM 5 is the main model I'm currently using. My usage with it is around 90,000 requests per month. Although its capability isn't the strongest, I think that because the quota is so large, it feels really great to use. For certain cases, I'll use the DeepSeek V4 model. Actually, my latest open-source project, vocnly, was developed on GLM 5. It's a local voice-input tool, and it can be seen as an open-source alternativ", "context": "", "use_case": "main coding model", "switched_from": "", "story": "Ask HN: Which model do you use for work?"}, {"id": 798700449, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "recommend", "quote": "$20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t", "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": "pays for many models", "use_case": "finding bugs", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}, {"id": 792584801, "item_id": 49536550, "url": "https://news.ycombinator.com/item?id=49536550", "by": "mark_l_watson", "date": "2026-09-02", "stance": "recommend", "quote": "I use Kimi K3 and GLM 5.3 to find old bugs and improve old code", "excerpt": "I use Kimi K3 and GLM 5.3 to find old bugs and improve old code, and would try Fable 5.1 if I could afford $50 for 1M output tokens (I am retired and all my research is self funded now) I like to start by prompting with \u201cexamine this code base for problems and improvements and write to IMPROVEMENTS.MD\u201d and then carefully look over the suggestions, and either fix myself or let the model+coding harness try.", "context": "retired, self-funded research", "use_case": "finding bugs, improving old code", "switched_from": "", "story": "Claude Fable 5.1 and Claude Mythos 5.1"}]}, {"text": " The most common complaints are Claude-like verbal tics that ignore style instructions", "cites": [{"id": 801813201, "item_id": 50113325, "url": "https://news.ycombinator.com/item?id=50113325", "by": "nullc", "date": "2026-10-16", "stance": "warn", "quote": "the claudisms in 5.3 are pathetic and drive me crazy", "excerpt": "It's not just you-- the claudisms in 5.3 are pathetic and drive me crazy, I was very sad to see it go in that direction and consider it a big step down in that respect. BUT OTOH the performance of 5.3-flash are impossible to argue with-- it has the same pathetic claude behavior full of \"Honest\" and \"lever\" and \"load bearing\" tripe... but it's scortchingly fast on hardware that is pretty slow running 5.2/5.3. As a res", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark Open"}, {"id": 793794944, "item_id": 49612184, "url": "https://news.ycombinator.com/item?id=49612184", "by": "klardotsh", "date": "2026-09-08", "stance": "warn", "quote": "is also atrocious about this", "excerpt": "GLM (both mainline and flash varieties), being trained to speak a very similar Claudeish, is also atrocious about this. My AGENTS.md demands all prose be in STE100, which is trying to solve a similar problem as the skill linked in OP. Getting GLM to STFU by AGENTS instruction is nigh impossible. I use a plugin for OMP/Pi to periodically inject system prompt reminders of output style, and it still largely ignores the ", "context": "", "use_case": "coding agent", "switched_from": "", "story": "I-have-ADHD: A skill to stop coding agents from burying the answer"}, {"id": 801878832, "item_id": 50117427, "url": "https://news.ycombinator.com/item?id=50117427", "by": "jubilee33", "date": "2026-10-16", "stance": "recommend", "quote": "the rest of the output is pretty amazing", "excerpt": "Never had that happen at all and using since launch as well, but I have a very custom harness running. My local machine went down however and I used their web API to repair it and talking to that felt much stupider, I think harness really matters Alot. I do get the really annoying LLM \"that's A, not B\" and \"load-bearing\" from time to time, those two tells stay no matter what I do even though the rest of the output is", "context": "uses a very custom harness", "use_case": "LLM with custom harness", "switched_from": "", "story": "Muse Spark Open"}]}, {"text": " and slower output than some rivals.", "cites": [{"id": 794860336, "item_id": 49678771, "url": "https://news.ycombinator.com/item?id=49678771", "by": "CuriouslyC", "date": "2026-09-13", "stance": "recommend", "quote": "They've been my two daily drivers since release, and I like GLM 5.3", "excerpt": "Any bench that puts GLM 5.3 ahead of 5.6 Sol is highly sus. They've been my two daily drivers since release, and I like GLM 5.3, but it's definitely not better than Sol, it's more ~Terra, while being significantly slower.", "context": "", "use_case": "daily driver", "switched_from": "", "story": "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"}, {"id": 792425873, "item_id": 49526617, "url": "https://news.ycombinator.com/item?id=49526617", "by": "dalekirkwood", "date": "2026-09-01", "stance": "recommend", "quote": "We use GLM 5.3 - its definitely slower but it gets the job done.", "excerpt": "I've tried Claude several times, but I don't find it very good. We use GLM 5.3 - its definitely slower but it gets the job done.", "context": "", "use_case": "team work", "switched_from": "Claude", "story": "Is it just me, or has Claude Opus gotten worse recently?"}, {"id": 800179904, "item_id": 50011244, "url": "https://news.ycombinator.com/item?id=50011244", "by": "jacquesm", "date": "2026-10-08", "stance": "recommend", "quote": "I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.", "excerpt": "If DS4.1 impresses you I would be really interested to see your comparison to GLM 5.3. I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.", "context": "", "use_case": "coding", "switched_from": "DeepSeek 4.1", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}], "praise": [{"label": "Frontier alternative", "summary": "Commenters say it is good enough to replace Anthropic and OpenAI models for most of their work.", "quotes": [{"id": 803899729, "item_id": 50243733, "url": "https://news.ycombinator.com/item?id=50243733", "by": "Sphax", "date": "2026-10-26", "stance": "recommend", "quote": "These chinese models are simply good enough for the vast majority of tasks I run", "excerpt": "I use Opus 5.5 daily at work and a mix of GLM 5.3 (Flash or not), Deepseek v4 (flash or pro) at home and while Opus 5.5 is more capable, in my opinion it matters for less than 5% of the work i do. These chinese models are simply good enough for the vast majority of tasks I run and when they're not I use Astra or Opus 5.5. Yes, leaving Opus 5.5 on all the time is comfortable when you pay the 90\u20ac plan but it's just not", "context": "", "use_case": "home use", "switched_from": "", "story": "Anthropic S-1"}, {"id": 791254881, "item_id": 49453430, "url": "https://news.ycombinator.com/item?id=49453430", "by": "Sphax", "date": "2026-08-26", "stance": "recommend", "quote": "It definitely can be a daily driver if you don\u2019t want to use Anthropic or OpenAI.", "excerpt": "Both can be true though. I had the max coding plan since january and I kept using with Pi since then, even though it wasn\u2019t as good as opus until glm 5.3. It definitely can be a daily driver if you don\u2019t want to use Anthropic or OpenAI. It\u2019s going to be even better with native vision now available. And i\u2019m not messing with my setup either.", "context": "", "use_case": "daily coding driver", "switched_from": "", "story": "GLM-5.3-Flash"}, {"id": 796718032, "item_id": 49794877, "url": "https://news.ycombinator.com/item?id=49794877", "by": "Sayrus", "date": "2026-09-21", "stance": "recommend", "quote": "Moved from Opus to GLM 5.2 to 5.3 and I've been pretty happy with the result.", "excerpt": "Same here. Moved from Opus to GLM 5.2 to 5.3 and I've been pretty happy with the result. Mainly, it doesn't hallucinate and convince itself of mistake so it's good at retrieving information or asking the user for it. Opus and Fable always state something, then try to \"prove\" it but end up convincing themselves of the wrong thing. Having subagents for retrieval and validation helped but were not enough.", "context": "", "use_case": "agentic coding and retrieval", "switched_from": "Opus", "story": "Fable 5 \u2013 Median thinking declined in August"}]}, {"label": "Code review", "summary": "Users report it finds bugs and handles reviews, debugging and reverse-engineering well.", "quotes": [{"id": 798700449, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "recommend", "quote": "$20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t", "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": "pays for many models", "use_case": "finding bugs", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}, {"id": 800000672, "item_id": 50000042, "url": "https://news.ycombinator.com/item?id=50000042", "by": "bigyabai", "date": "2026-10-07", "stance": "recommend", "quote": "Full 5.3 has a scary-good grasp of debugging assembly, QEMU and hex dumps in my experience", "excerpt": "I've been using GLM 5.3 and 5.3 Flash to reverse-engineer some old firmwares, and it hasn't protested at all. Full 5.3 has a scary-good grasp of debugging assembly, QEMU and hex dumps in my experience, it would make for a good \"sleuth\" model to find potential vulns. 5.3 Flash is closer to 5.5 Sonnet/6 Luna capabilities-wise, but still smart enough to implement the easy fixes or steer your red team agent. It's been ab", "context": "", "use_case": "reverse-engineering firmware, vuln finding", "switched_from": "Claude Code", "story": "Ask HN: Which frontier model can do code security reviews"}, {"id": 792521680, "item_id": 49532605, "url": "https://news.ycombinator.com/item?id=49532605", "by": "taylorhou", "date": "2026-09-02", "stance": "recommend", "quote": "today was the first time ever that a local model (GLM5.3 8-bit) was able to match fable5 in our tests.", "excerpt": "i have a 512gb ram m3 ultra mac studio setup with a gas city that runs one of my companies. today was the first time ever that a local model (GLM5.3 8-bit) was able to match fable5 in our tests. GLM-5.3-Flash at true 8-bit: 341 GB on disk, 328 GB resident, 288 experts across 46 layers, loads in 65 seconds. \u2022 18.7 tokens/s generation, 35 tokens/s prompt, on a desk, on a $0 per-token bill. \u2022 Runs beside our whole agent", "context": "runs a company with a Mac Studio agent setup", "use_case": "local inference for company agents", "switched_from": "", "story": "My local model setup on an M4 Pro Mac Mini"}]}, {"label": "Low cost", "summary": "Commenters cite cheap per-request costs and large subscription quotas.", "quotes": [{"id": 800362641, "item_id": 50022665, "url": "https://news.ycombinator.com/item?id=50022665", "by": "cco", "date": "2026-10-09", "stance": "recommend", "quote": "It is basically free, half a cent per turn maybe", "excerpt": "Yeah maybe I'll play around with different precision, I did see improvement when I went from fp4 to full fidelity though. This is my setup for Home Assistant voice, parakeet for STT, GLM 5.3 to generate responses, and Kokoro for TTS. I use local routing for simple commands like turn on the lights, but if I want to ask questions or something, it gets routed to GLM 5.3. It is basically free, half a cent per turn maybe,", "context": "", "use_case": "voice assistant responses", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 797804800, "item_id": 49862800, "url": "https://news.ycombinator.com/item?id=49862800", "by": "laoxingAI", "date": "2026-09-27", "stance": "recommend", "quote": "because the quota is so large, it feels really great to use", "excerpt": "GLM 5 is the main model I'm currently using. My usage with it is around 90,000 requests per month. Although its capability isn't the strongest, I think that because the quota is so large, it feels really great to use. For certain cases, I'll use the DeepSeek V4 model. Actually, my latest open-source project, vocnly, was developed on GLM 5. It's a local voice-input tool, and it can be seen as an open-source alternativ", "context": "", "use_case": "main coding model", "switched_from": "", "story": "Ask HN: Which model do you use for work?"}, {"id": 794775872, "item_id": 49673492, "url": "https://news.ycombinator.com/item?id=49673492", "by": "Havoc", "date": "2026-09-12", "stance": "recommend", "quote": "GLM5.3 - I'm on one of the ancient plans, meaning basically unlimited.", "excerpt": "GLM5.3 - I'm on one of the ancient plans, meaning basically unlimited. ...and then sprinkle in some other models when i think a second opinion will help", "context": "", "use_case": "default coding model", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}]}, {"label": "Fewer hallucinations", "summary": "Some say it hallucinates less than DeepSeek or Opus and behaves consistently over time.", "quotes": [{"id": 800365040, "item_id": 50022815, "url": "https://news.ycombinator.com/item?id=50022815", "by": "pimeys", "date": "2026-10-09", "stance": "recommend", "quote": "I like to do some discussions and back and forth with GLM. It doesn't hallucinate as much or gaslight like DeepSeek does.", "excerpt": "I like to do some discussions and back and forth with GLM. It doesn't hallucinate as much or gaslight like DeepSeek does. DeepSeek is great if you have a plan and you let it go. Also can plan a bit. But it has this sparse attention and especially the index_topk is too small in common deployments so it doesn't \"see\" all the context. And it then imagines things which is annoying if you chat with it about stuff you deve", "context": "", "use_case": "discussion and planning", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 796718032, "item_id": 49794877, "url": "https://news.ycombinator.com/item?id=49794877", "by": "Sayrus", "date": "2026-09-21", "stance": "recommend", "quote": "Moved from Opus to GLM 5.2 to 5.3 and I've been pretty happy with the result.", "excerpt": "Same here. Moved from Opus to GLM 5.2 to 5.3 and I've been pretty happy with the result. Mainly, it doesn't hallucinate and convince itself of mistake so it's good at retrieving information or asking the user for it. Opus and Fable always state something, then try to \"prove\" it but end up convincing themselves of the wrong thing. Having subagents for retrieval and validation helped but were not enough.", "context": "", "use_case": "agentic coding and retrieval", "switched_from": "Opus", "story": "Fable 5 \u2013 Median thinking declined in August"}, {"id": 804024530, "item_id": 50251533, "url": "https://news.ycombinator.com/item?id=50251533", "by": "lousken", "date": "2026-10-26", "stance": "recommend", "quote": "while GLM, Kimi and others stay the same", "excerpt": "My issue with anthropic and openai is that if I use a model like e.g. Sonnet 5 I don't always get full Sonnet 5, sometimes it's dumber, sometimes it is smarter (mostly dumber though), while GLM, Kimi and others stay the same. So if I rely on AI for things I better make sure the platform is stable and does not introduce hidden changes. Why is opus 5.5 suddenly a lot dumber? Who knows.", "context": "", "use_case": "", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}]}, {"label": "Flash speed", "summary": "The Flash variant is described as very fast, even on slower hardware.", "quotes": [{"id": 801813200, "item_id": 50113325, "url": "https://news.ycombinator.com/item?id=50113325", "by": "nullc", "date": "2026-10-16", "stance": "recommend", "quote": "I don't enjoy using it the way I enjoyed GLM-5.2", "excerpt": "It's not just you-- the claudisms in 5.3 are pathetic and drive me crazy, I was very sad to see it go in that direction and consider it a big step down in that respect. BUT OTOH the performance of 5.3-flash are impossible to argue with-- it has the same pathetic claude behavior full of \"Honest\" and \"lever\" and \"load bearing\" tripe... but it's scortchingly fast on hardware that is pretty slow running 5.2/5.3. As a res", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark Open"}, {"id": 800199232, "item_id": 50012452, "url": "https://news.ycombinator.com/item?id=50012452", "by": "pjerem", "date": "2026-10-08", "stance": "recommend", "quote": "I used GLM-5.3 as usual from Ollama cloud and it was so fast it generated entire documents like instantly.", "excerpt": "IDK what happened today but I used GLM-5.3 as usual from Ollama cloud and it was so fast it generated entire documents like instantly. The reasoning and the result document were done after less than 1 or 2 seconds. Have Ollama suddenly bought GPU capacity?", "context": "", "use_case": "document generation", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}, {"label": "Language nuance", "summary": "One user picks it for understanding nuances in Chinese language study.", "quotes": [{"id": 792989712, "item_id": 49561857, "url": "https://news.ycombinator.com/item?id=49561857", "by": "navigate8310", "date": "2026-09-04", "stance": "recommend", "quote": "I specifically use it with glm 5.3 as it is the most language specific LLM that understands nuances.", "excerpt": "I OCR'd my Chinese textbooks and made a stateless MCP that allows me to ground my Chinese language studies according to the textbook only. With this I can start a quiz, understand differences between words that have similar meanings knowing no extra grammar is fed when reviewing. I specifically use it with glm 5.3 as it is the most language specific LLM that understands nuances. Here's the repository: https://github.", "context": "", "use_case": "Chinese language study", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}]}], "caveats": [{"label": "Claude-like prose", "summary": "Version 5.3 uses Claude-style phrases and largely ignores instructions about output style.", "quotes": [{"id": 801813201, "item_id": 50113325, "url": "https://news.ycombinator.com/item?id=50113325", "by": "nullc", "date": "2026-10-16", "stance": "warn", "quote": "the claudisms in 5.3 are pathetic and drive me crazy", "excerpt": "It's not just you-- the claudisms in 5.3 are pathetic and drive me crazy, I was very sad to see it go in that direction and consider it a big step down in that respect. BUT OTOH the performance of 5.3-flash are impossible to argue with-- it has the same pathetic claude behavior full of \"Honest\" and \"lever\" and \"load bearing\" tripe... but it's scortchingly fast on hardware that is pretty slow running 5.2/5.3. As a res", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark Open"}, {"id": 793794944, "item_id": 49612184, "url": "https://news.ycombinator.com/item?id=49612184", "by": "klardotsh", "date": "2026-09-08", "stance": "warn", "quote": "is also atrocious about this", "excerpt": "GLM (both mainline and flash varieties), being trained to speak a very similar Claudeish, is also atrocious about this. My AGENTS.md demands all prose be in STE100, which is trying to solve a similar problem as the skill linked in OP. Getting GLM to STFU by AGENTS instruction is nigh impossible. I use a plugin for OMP/Pi to periodically inject system prompt reminders of output style, and it still largely ignores the ", "context": "", "use_case": "coding agent", "switched_from": "", "story": "I-have-ADHD: A skill to stop coding agents from burying the answer"}, {"id": 801878832, "item_id": 50117427, "url": "https://news.ycombinator.com/item?id=50117427", "by": "jubilee33", "date": "2026-10-16", "stance": "recommend", "quote": "the rest of the output is pretty amazing", "excerpt": "Never had that happen at all and using since launch as well, but I have a very custom harness running. My local machine went down however and I used their web API to repair it and talking to that felt much stupider, I think harness really matters Alot. I do get the really annoying LLM \"that's A, not B\" and \"load-bearing\" from time to time, those two tells stay no matter what I do even though the rest of the output is", "context": "uses a very custom harness", "use_case": "LLM with custom harness", "switched_from": "", "story": "Muse Spark Open"}]}, {"label": "Slower output", "summary": "Several users find GLM 5.3 slower than alternatives such as Sol or DeepSeek.", "quotes": [{"id": 794860336, "item_id": 49678771, "url": "https://news.ycombinator.com/item?id=49678771", "by": "CuriouslyC", "date": "2026-09-13", "stance": "recommend", "quote": "They've been my two daily drivers since release, and I like GLM 5.3", "excerpt": "Any bench that puts GLM 5.3 ahead of 5.6 Sol is highly sus. They've been my two daily drivers since release, and I like GLM 5.3, but it's definitely not better than Sol, it's more ~Terra, while being significantly slower.", "context": "", "use_case": "daily driver", "switched_from": "", "story": "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"}, {"id": 792425873, "item_id": 49526617, "url": "https://news.ycombinator.com/item?id=49526617", "by": "dalekirkwood", "date": "2026-09-01", "stance": "recommend", "quote": "We use GLM 5.3 - its definitely slower but it gets the job done.", "excerpt": "I've tried Claude several times, but I don't find it very good. We use GLM 5.3 - its definitely slower but it gets the job done.", "context": "", "use_case": "team work", "switched_from": "Claude", "story": "Is it just me, or has Claude Opus gotten worse recently?"}, {"id": 800179904, "item_id": 50011244, "url": "https://news.ycombinator.com/item?id=50011244", "by": "jacquesm", "date": "2026-10-08", "stance": "recommend", "quote": "I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.", "excerpt": "If DS4.1 impresses you I would be really interested to see your comparison to GLM 5.3. I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.", "context": "", "use_case": "coding", "switched_from": "DeepSeek 4.1", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}, {"label": "Not frontier", "summary": "Some say it trails top proprietary models and Kimi in capability.", "quotes": [{"id": 790874144, "item_id": 49429634, "url": "https://news.ycombinator.com/item?id=49429634", "by": "petesergeant", "date": "2026-08-25", "stance": "recommend", "quote": "I switch to GLM5.3, and it's not quite there, but it's good enough for productive work.", "excerpt": "Someone else having been too early on a prediction has little bearing on my prediction. A year ago almost nobody was using open models as daily drivers, today they are. When I run out of Fable and Sol credits in a week, I switch to GLM5.3, and it's not quite there, but it's good enough for productive work.", "context": "", "use_case": "coding fallback", "switched_from": "", "story": "Ox-Alpha Is GLM?"}, {"id": 794860336, "item_id": 49678771, "url": "https://news.ycombinator.com/item?id=49678771", "by": "CuriouslyC", "date": "2026-09-13", "stance": "recommend", "quote": "They've been my two daily drivers since release, and I like GLM 5.3", "excerpt": "Any bench that puts GLM 5.3 ahead of 5.6 Sol is highly sus. They've been my two daily drivers since release, and I like GLM 5.3, but it's definitely not better than Sol, it's more ~Terra, while being significantly slower.", "context": "", "use_case": "daily driver", "switched_from": "", "story": "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"}, {"id": 791686288, "item_id": 49480393, "url": "https://news.ycombinator.com/item?id=49480393", "by": "revolvingthrow", "date": "2026-08-28", "stance": "recommend", "quote": "GLM 5.3 is probably the sweet spot open weights model", "excerpt": "GLM 5.3 is probably the sweet spot open weights model if you want to go beyond deepseek flash or the new glm flash. I used it with pi and had a fairly good time, especially since it\u2019s less touchy about cyber and whatnot than the US guys. It\u2019s slightly behind Kimi in ability but it\u2019s a lot easier to run it, I\u2019d expect prices (and speed!) from third parties to be noticeably better. Assuming you\u2019re willing to drop a fat", "context": "", "use_case": "open-weight coding model", "switched_from": "", "story": "GLM-5.3 is now open-weight"}]}, {"label": "Censorship", "summary": "One team reports 5-8% of bulk data-crunching requests get censored without a response.", "quotes": [{"id": 796942496, "item_id": 49808906, "url": "https://news.ycombinator.com/item?id=49808906", "by": "system2", "date": "2026-09-22", "stance": "warn", "quote": "roughly 5-8% (depending on the day) gets censored and doesn't get a response", "excerpt": "Except for the censorship. We use it for massive data crunching, and roughly 5-8% (depending on the day) gets censored and doesn't get a response. We switched to Mimo 2.6, which is relatively better. For censored stuff, we use Sonnet and OpenAI Nano models. Also Mimo 2.6 is roughly 30% cheaper. Without batch.", "context": "", "use_case": "massive data crunching", "switched_from": "", "story": "GPT-6 Sol and Luna"}]}, {"label": "Agent safety", "summary": "Users report it acting outside granted permissions and departing from the user's spec.", "quotes": [{"id": 801073681, "item_id": 50067105, "url": "https://news.ycombinator.com/item?id=50067105", "by": "crossroadsguy", "date": "2026-10-13", "stance": "warn", "quote": "one day Codex+GLM went ahead and did things in my ~/.dotfiles folder which I had granted only READ access for", "excerpt": "I was delaying it but one day Codex+GLM went ahead and did things in my ~/.dotfiles folder which I had granted only READ access for. I asked and I was given a reason which I didn't understand and didn't really want to. Right then I used sandbox-exec/safehouse (macOS) and tightened every harness installed (and the one not even installed, lest I install it later and forget to add/track them in the sb zsh init script). ", "context": "macOS user", "use_case": "model behind coding agent", "switched_from": "", "story": "Codex CLI installs a persistent, self-updating background daemon by default"}, {"id": 797621888, "item_id": 49851368, "url": "https://news.ycombinator.com/item?id=49851368", "by": "_jonas", "date": "2026-09-25", "stance": "warn", "quote": "GLM 5.3 knows that its implementation violates user requirements yet sticks with it after imagining what a hypothetical grader will check", "excerpt": "I audited thousands of agent rollouts in DeepSWE-1.1. Over 80% contained reasoning about an imagined grader. Yet no grader/verifier is mentioned in prompts nor accessible to the agents. Agents reasoned things like: \"Let me look at the problem from the grader's perspective\" and referred to \"hidden tests\", \"test authors\", and \"the checker\". I found this behavior across all six frontier models analyzed, including recent", "context": "AI researcher auditing agent rollouts", "use_case": "coding agent tasks", "switched_from": "", "story": "Speculative Reward Hacking in Coding Agents"}]}, {"label": "Capacity and cost", "summary": "Commenters mention capacity constraints, maxed-out subscriptions and high prices at some providers.", "quotes": [{"id": 796914498, "item_id": 49807156, "url": "https://news.ycombinator.com/item?id=49807156", "by": "gizmodo59", "date": "2026-09-22", "stance": "recommend", "quote": "Even some oss models like glm are good", "excerpt": "yeah I used to love claude! but these days it refuses and responds as if its like a big brother. glad competition exists and for the past few months codex has been significantly better. Even some oss models like glm are good but they dont have enough compute and get capacity constraints", "context": "", "use_case": "", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 799694545, "item_id": 49980909, "url": "https://news.ycombinator.com/item?id=49980909", "by": "phillc73", "date": "2026-10-06", "stance": "recommend", "quote": "this worked very well and powered through a tonne of work", "excerpt": "I'm at a loss as to what to do now. I've been wanting to support Mistral for so long. I struggled on with Mistral Medium 3.5 for longer than I should have (although I also think it taught me some valuable process lessons). Recently I switched to the Mistral hosted GLM-5.3, this worked very well and powered through a tonne of work. Unfortunately, I also completely maxed out two subscriptions within the space of six da", "context": "", "use_case": "coding", "switched_from": "Mistral Medium 3.5", "story": "Mistral Large 4"}, {"id": 800365040, "item_id": 50022815, "url": "https://news.ycombinator.com/item?id=50022815", "by": "pimeys", "date": "2026-10-09", "stance": "recommend", "quote": "I like to do some discussions and back and forth with GLM. It doesn't hallucinate as much or gaslight like DeepSeek does.", "excerpt": "I like to do some discussions and back and forth with GLM. It doesn't hallucinate as much or gaslight like DeepSeek does. DeepSeek is great if you have a plan and you let it go. Also can plan a bit. But it has this sparse attention and especially the index_topk is too small in common deployments so it doesn't \"see\" all the context. And it then imagines things which is annoying if you chat with it about stuff you deve", "context": "", "use_case": "discussion and planning", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}], "who": [{"by": "scotty79", "context": "built their own browser with agents", "url": "https://news.ycombinator.com/item?id=50136679", "date": "2026-10-18"}, {"by": "tough", "context": "uses it at work", "url": "https://news.ycombinator.com/item?id=50118387", "date": "2026-10-16"}, {"by": "jubilee33", "context": "uses a very custom harness", "url": "https://news.ycombinator.com/item?id=50117427", "date": "2026-10-16"}, {"by": "denkmoon", "context": "uses frontier models at work", "url": "https://news.ycombinator.com/item?id=50013406", "date": "2026-10-08"}, {"by": "phillc73", "context": "Mistral user", "url": "https://news.ycombinator.com/item?id=49932202", "date": "2026-10-02"}, {"by": "petesergeant", "context": "pays for many models", "url": "https://news.ycombinator.com/item?id=49918778", "date": "2026-10-01"}, {"by": "abalashov", "context": "individual contributor", "url": "https://news.ycombinator.com/item?id=49815221", "date": "2026-09-23"}, {"by": "vardalab", "context": "homelab user", "url": "https://news.ycombinator.com/item?id=49805228", "date": "2026-09-22"}, {"by": "poslathian", "context": "does modeling, commercial analysis and math, not primarily code", "url": "https://news.ycombinator.com/item?id=49793444", "date": "2026-09-21"}, {"by": "softwarewright", "context": "single person LLC", "url": "https://news.ycombinator.com/item?id=49591330", "date": "2026-09-06"}, {"by": "mark_l_watson", "context": "retired, self-funded research", "url": "https://news.ycombinator.com/item?id=49536550", "date": "2026-09-02"}, {"by": "taylorhou", "context": "runs a company with a Mac Studio agent setup", "url": "https://news.ycombinator.com/item?id=49532605", "date": "2026-09-02"}], "tags": ["for coding", "for code review", "self-hostable", "for agentic workflows", "for Chinese language study"], "use_cases": ["coding", "ai coding", "coding model", "planning", "coding tasks", "code review"], "compared": [{"slug": "kimi", "name": "Kimi", "co": 73, "switched_from": 4, "switched_to": 2}, {"slug": "claude", "name": "Claude", "co": 56, "switched_from": 14, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 75, "switched_from": 4, "switched_to": 0}, {"slug": "deepseek", "name": "DeepSeek", "co": 68, "switched_from": 1, "switched_to": 2}, {"slug": "opencode", "name": "OpenCode", "co": 55, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 41, "switched_from": 4, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 34, "switched_from": 0, "switched_to": 2}, {"slug": "claude-sonnet", "name": "Claude Sonnet", "co": 31, "switched_from": 3, "switched_to": 0}], "makers": [{"id": 800358802, "item_id": 50022425, "url": "https://news.ycombinator.com/item?id=50022425", "by": "erans", "date": "2026-10-09", "stance": "neutral", "quote": "We also have GLM 5.3 (with vision!) and GLM 5.3 Flash - all included.", "excerpt": "I've been using DS 4.1 Flash for a while now as my main workhorse. It's amazing. It's fast and it is also a GREAT debugger - it might not always find the best solution but it will definitely find the problem quickly. I'm also the CEO of a new company - LunaRoute - so if you want private, fixed cost, we run our own server in the US type of DeepSeek 4.1 Flash check out https://www.lunaroute.com If you want a trial, hit", "context": "", "use_case": "hosted LLM", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 782038240, "item_id": 48877390, "url": "https://news.ycombinator.com/item?id=48877390", "by": "i386", "date": "2026-07-11", "stance": "neutral", "quote": "we are developing a custom GLM DSA Metal graph.", "excerpt": "The lab features two Mac Studios: an Apple M3 Ultra (32 CPU cores, 80 GPU cores, 256 GB unified memory) and an Apple M1 Ultra (20 CPU cores, 48 GPU cores, 128 GB unified memory), both connected via 1Gbit Ethernet. We use a customized Q2 quantization that preserves sensitive tensors at Q8. To reduce compute time per layer, we are developing a custom GLM DSA Metal graph. While we are not yet approaching MTP, we plan to", "context": "", "use_case": "distributed inference on Mac Studios", "switched_from": "", "story": "Mesh LLM: distributed AI computing on iroh"}], "threads": [{"url": "https://news.ycombinator.com/item?id=48518684", "title": "GLM 5.2 Is Out", "mentions": 10}, {"url": "https://news.ycombinator.com/item?id=49294997", "title": "GLM-5.3: Frontier Coding with Emergent Cyber Capabilities", "mentions": 9}, {"url": "https://news.ycombinator.com/item?id=48626866", "title": "GLM 5.2 vs. Opus", "mentions": 9}, {"url": "https://news.ycombinator.com/item?id=48709670", "title": "Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks", "mentions": 8}, {"url": "https://news.ycombinator.com/item?id=48809877", "title": "GLM 5.2 and the coming AI margin collapse", "mentions": 7}, {"url": "https://news.ycombinator.com/item?id=50107379", "title": "Muse Spark Open", "mentions": 6}], "sentiment_by_month": {"2025-11": {"recommend": 5, "neutral": 2}, "2025-12": {"recommend": 4, "compare": 1}, "2026-01": {"neutral": 3, "recommend": 6}, "2026-02": {"neutral": 2}, "2026-03": {"neutral": 1, "recommend": 2}, "2026-04": {"recommend": 8, "warn": 1, "neutral": 3}, "2026-05": {"warn": 1, "recommend": 5, "neutral": 1}, "2026-06": {"neutral": 16, "recommend": 44, "compare": 5, "warn": 7}, "2026-07": {"compare": 12, "recommend": 36, "neutral": 15, "warn": 3}, "2026-08": {"neutral": 8, "compare": 5, "recommend": 25, "warn": 2}, "2026-09": {"neutral": 15, "compare": 2, "recommend": 19, "warn": 3}, "2026-10": {"recommend": 23, "compare": 5, "neutral": 10, "warn": 3}}, "quotes": [{"id": 804914322, "item_id": 50307145, "url": "https://news.ycombinator.com/item?id=50307145", "by": "Imustaskforhelp", "date": "2026-10-30", "stance": "recommend", "quote": "My fork was created with the help of GLM 5.3 (an open-weights model)", "excerpt": "> The week after that: everything is written in ASM. This is an genuinely good minimalist good editor that is created in mostly assembly that was created with the help of AI[0] I maintain a fork of it which basically adds scratchpad ability to it and is something that I use daily myself for what it's worth[1] My fork was created with the help of GLM 5.3 (an open-weights model) The future is already here in some sense", "context": "", "use_case": "writing assembly code", "switched_from": "", "story": "Show HN: A working Nintendo in ~1GB of Qwen weights"}, {"id": 804024530, "item_id": 50251533, "url": "https://news.ycombinator.com/item?id=50251533", "by": "lousken", "date": "2026-10-26", "stance": "recommend", "quote": "while GLM, Kimi and others stay the same", "excerpt": "My issue with anthropic and openai is that if I use a model like e.g. Sonnet 5 I don't always get full Sonnet 5, sometimes it's dumber, sometimes it is smarter (mostly dumber though), while GLM, Kimi and others stay the same. So if I rely on AI for things I better make sure the platform is stable and does not introduce hidden changes. Why is opus 5.5 suddenly a lot dumber? Who knows.", "context": "", "use_case": "", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}, {"id": 803903026, "item_id": 50243939, "url": "https://news.ycombinator.com/item?id=50243939", "by": "criley2", "date": "2026-10-26", "stance": "compare", "quote": "GLM 5.3 (max) is $2.01", "excerpt": "I use Opus 5.5 at work and I use Sonnet 5.5 at home. Sonnet 5.5 medium according to AA cost per task is $0.48 per task, while GLM 5.3 (max) is $2.01 (opus 5.5 high is $1.82). GLM 5.3 flash is $0.28 per task and Deepseek 4.1 flash 1017 is $0.26. So it seems like Sonnet 5.5 medium, GLM 5.3 flash and Deepseek V4.1 flash 1017 are all in a similar space in capacity and price, however the $20 anthropic sub will get you lik", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic S-1"}, {"id": 803899729, "item_id": 50243733, "url": "https://news.ycombinator.com/item?id=50243733", "by": "Sphax", "date": "2026-10-26", "stance": "recommend", "quote": "These chinese models are simply good enough for the vast majority of tasks I run", "excerpt": "I use Opus 5.5 daily at work and a mix of GLM 5.3 (Flash or not), Deepseek v4 (flash or pro) at home and while Opus 5.5 is more capable, in my opinion it matters for less than 5% of the work i do. These chinese models are simply good enough for the vast majority of tasks I run and when they're not I use Astra or Opus 5.5. Yes, leaving Opus 5.5 on all the time is comfortable when you pay the 90\u20ac plan but it's just not", "context": "", "use_case": "home use", "switched_from": "", "story": "Anthropic S-1"}, {"id": 803853440, "item_id": 50240840, "url": "https://news.ycombinator.com/item?id=50240840", "by": "mattlondon", "date": "2026-10-26", "stance": "recommend", "quote": "I had a really nice time with GLM5.2 for a month or two", "excerpt": "I think, despite the desperate attempt at IBM to remain relevant (and in business), their CEO has a point here that do you really need SOTA models for everything? I had a really nice time with GLM5.2 for a month or two - it was, in my experience, approx Opus 4.5ish level of capability when I think Opus 4.8 was the new hotness Even today, I use Gemini 3.8 Flash as my daily driver for most coding. Its fast and good, ev", "context": "", "use_case": "coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 803556581, "item_id": 50222286, "url": "https://news.ycombinator.com/item?id=50222286", "by": "potsandpans", "date": "2026-10-24", "stance": "compare", "quote": "glm and kimi k.3, expensive, slow, ultimately not that much better than deepseek flash for this task.", "excerpt": "I recently just crossed the threshold for 100% decompilation of a PlayStation game. I used a lot of models in the process, and I feel like this is a good demonstration the \"sauce\" that opus has. The harness I've built for it is pretty straight forward: split binary into individual functions, give the agent a bunch of small tools to diff output with underlying binary, make them wrote clean c until there's a certified ", "context": "decompiling a PlayStation game", "use_case": "long-context compiler research", "switched_from": "", "story": "Kimi K3.1 scores 55 on Artificial Analysis, placed on the Pareto line"}, {"id": 803495921, "item_id": 50218495, "url": "https://news.ycombinator.com/item?id=50218495", "by": "jackbeanstalk20", "date": "2026-10-24", "stance": "neutral", "quote": "We already switched from openAI to GLM", "excerpt": "I think my company will switch to this soon. We already switched from openAI to GLM and now this is just a better model with the same price", "context": "", "use_case": "company LLM", "switched_from": "OpenAI", "story": "Kimi K3.1 Pro and K3.1 Pro Highspeed"}, {"id": 803314625, "item_id": 50207164, "url": "https://news.ycombinator.com/item?id=50207164", "by": "phillc73", "date": "2026-10-23", "stance": "neutral", "quote": "GML-5.3, GLM5.3 Flash", "excerpt": "I use Maki[1] harness and GML-5.3, GLM5.3 Flash and Deepseek-4.1 Flash 1017, with a little bit of MiMo-2.6. The key I've found is a strong skill. At the beginning, sure there were problems. However, I implemented an AGENTS rule that said if a Janet script failed more than twice on the same \"gotcha\", the correct syntax was added to the skill. The skill is regularly reviewed, consolidated and pruned. The Janet skill is", "context": "", "use_case": "coding with Janet", "switched_from": "", "story": "Jank \u2013 The native Clojure dialect with seamless C++ interop"}, {"id": 803276610, "item_id": 50204788, "url": "https://news.ycombinator.com/item?id=50204788", "by": "svcrunch", "date": "2026-10-23", "stance": "neutral", "quote": "using GLM 5.3 failed.", "excerpt": "Along these lines, we used Codex to collaboratively build an alloy model for verifying the authorization model of GoodMem. After building the model, we implemented the code based on it, and, while there could be a gap in the translation process, several hours of red-teaming the server (w/attacker source code access) to try and produce a privilege escalation attack using GLM 5.3 failed. Alloy is a tool I tried to lear", "context": "", "use_case": "red-teaming server", "switched_from": "", "story": "LLMs are making formal software verification feasible at a much larger scale"}, {"id": 802940817, "item_id": 50183801, "url": "https://news.ycombinator.com/item?id=50183801", "by": "consocio", "date": "2026-10-21", "stance": "neutral", "quote": "GLM 5.3 just wrote it to audit all my php sites.", "excerpt": "https://github.com/consocio/php2shell-audit/ GLM 5.3 just wrote it to audit all my php sites. I hope it is useful to you", "context": "", "use_case": "writing audit tool", "switched_from": "", "story": "Tell HN: 2x PHP RCE CVEs with CVSS 10.0 Incoming"}, {"id": 802861570, "item_id": 50178848, "url": "https://news.ycombinator.com/item?id=50178848", "by": "_pdp_", "date": "2026-10-21", "stance": "neutral", "quote": "plenty of companies in UK and Europe that provide serverless access to GLM, DeepSeek etc.", "excerpt": "Someone asked me this morning if I consider Muse a privacy risk. Lol. I do. But to be honest this is all temporary. Muse, Grok, Dots will have users for the foreseeable future but there will be viable options for self-hosting too. I am already doing it https://github.com/pdparchitect/noodle/ The Hub powers the entire family inference needs through a single device - 4 users - 8 device about 50 agents - mixture of loca", "context": "", "use_case": "privacy-friendly cloud inference", "switched_from": "", "story": "Muse exposes users' personal and business secrets when they share conversations"}, {"id": 802256305, "item_id": 50141019, "url": "https://news.ycombinator.com/item?id=50141019", "by": "pimeys", "date": "2026-10-18", "stance": "recommend", "quote": "If it's mission-critical code, do a security review with GLM 5.3.", "excerpt": "I also used to plan with more expensive models like you did, but now I just do planning with DeepSeek too and don't see much difference. I use the omp plan mode and iterate on the text until I'm happy with it. Then clear context, give the plan to DeepSeek again for implementation. If it's mission-critical code, do a security review with GLM 5.3. Otherwise go manually through the code and ask for changes if needed. Wo", "context": "", "use_case": "security review", "switched_from": "", "story": "DeepSeek-v4.1-Flash-1017"}, {"id": 802186864, "item_id": 50136679, "url": "https://news.ycombinator.com/item?id=50136679", "by": "scotty79", "date": "2026-10-18", "stance": "neutral", "quote": "what glm-5.3 responded with to my question", "excerpt": "tl;dr They argue AI abolition is only possible alongside the abolition of capitalism, since AI's harms are integral to capitalism itself. Their idea of AI abolition aims at a liberatory alternative, which they define as \"a revolution from the left as an alternative to global technofascism.\" The above is my personal selection from what glm-5.3 responded with to my question \"What's the main point of this?\" asked in the", "context": "built their own browser with agents", "use_case": "summarizing web pages", "switched_from": "", "story": "Abolish AI Manifesto"}, {"id": 802095809, "item_id": 50130988, "url": "https://news.ycombinator.com/item?id=50130988", "by": "phillc73", "date": "2026-10-17", "stance": "recommend", "quote": "Quite happily chugging along with a nice balance across them now.", "excerpt": "I\u2019ll add Melious.[1] I feel like I\u2019m getting good value out of my subscription and they have the cheapest GLM-5.3 API rates I could find in Europe. I moved to them recently from Mistral for the better prices. They do have a slightly different daily inference capacity allowance, but it\u2019s actually not too bad once used to it. I was forced to up my game and figure out what GLM-5.3 Flash and Deepseek-4.1 Flash could actu", "context": "", "use_case": "general LLM tasks", "switched_from": "", "story": "DeepSeek-v4.1-Flash-1017"}, {"id": 801997936, "item_id": 50124871, "url": "https://news.ycombinator.com/item?id=50124871", "by": "JoTurk", "date": "2026-10-16", "stance": "warn", "quote": "It didn't find any of the CVEs oss-scanner found.", "excerpt": "I'm not sure if it's a user issue, but someone sent me a long markdown of issues GLM 5.3 found, and most of them are panics (we don't consider panics to be CVEs) It didn't find any of the CVEs oss-scanner found. We don't have access to much AI tools our-self since Pion is free and opensource and we don't get paid :) so we rely on token donations for review and fixes", "context": "open source maintainer of Pion", "use_case": "security bug finding", "switched_from": "", "story": "Tell HN: Anthropic found 36 bugs (6 CVEs) in Pion, OpenAI missed them"}, {"id": 801894192, "item_id": 50118387, "url": "https://news.ycombinator.com/item?id=50118387", "by": "tough", "date": "2026-10-16", "stance": "neutral", "quote": "We use GLM at work and YMMV a lot depending on the provider.", "excerpt": "We use GLM at work and YMMV a lot depending on the provider. So i guess some have bugs on their inference pipeline, or serve too agressive quants", "context": "uses it at work", "use_case": "work LLM use", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801878832, "item_id": 50117427, "url": "https://news.ycombinator.com/item?id=50117427", "by": "jubilee33", "date": "2026-10-16", "stance": "recommend", "quote": "the rest of the output is pretty amazing", "excerpt": "Never had that happen at all and using since launch as well, but I have a very custom harness running. My local machine went down however and I used their web API to repair it and talking to that felt much stupider, I think harness really matters Alot. I do get the really annoying LLM \"that's A, not B\" and \"load-bearing\" from time to time, those two tells stay no matter what I do even though the rest of the output is", "context": "uses a very custom harness", "use_case": "LLM with custom harness", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801813200, "item_id": 50113325, "url": "https://news.ycombinator.com/item?id=50113325", "by": "nullc", "date": "2026-10-16", "stance": "recommend", "quote": "I don't enjoy using it the way I enjoyed GLM-5.2", "excerpt": "It's not just you-- the claudisms in 5.3 are pathetic and drive me crazy, I was very sad to see it go in that direction and consider it a big step down in that respect. BUT OTOH the performance of 5.3-flash are impossible to argue with-- it has the same pathetic claude behavior full of \"Honest\" and \"lever\" and \"load bearing\" tripe... but it's scortchingly fast on hardware that is pretty slow running 5.2/5.3. As a res", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801813201, "item_id": 50113325, "url": "https://news.ycombinator.com/item?id=50113325", "by": "nullc", "date": "2026-10-16", "stance": "warn", "quote": "the claudisms in 5.3 are pathetic and drive me crazy", "excerpt": "It's not just you-- the claudisms in 5.3 are pathetic and drive me crazy, I was very sad to see it go in that direction and consider it a big step down in that respect. BUT OTOH the performance of 5.3-flash are impossible to argue with-- it has the same pathetic claude behavior full of \"Honest\" and \"lever\" and \"load bearing\" tripe... but it's scortchingly fast on hardware that is pretty slow running 5.2/5.3. As a res", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801780065, "item_id": 50111254, "url": "https://news.ycombinator.com/item?id=50111254", "by": "Shebanator", "date": "2026-10-15", "stance": "compare", "quote": "GLM is still better at planning.", "excerpt": "Model sizes aren't directly comparable, and they aren't even that relevant. I care about result quality, cost, and speed, not size. I switched to deepseek because it was giving me better coding results than GLM, and for far less cost. GLM is still better at planning.", "context": "", "use_case": "planning", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801729696, "item_id": 50108106, "url": "https://news.ycombinator.com/item?id=50108106", "by": "eknkc", "date": "2026-10-15", "stance": "recommend", "quote": "only open model I use extensively", "excerpt": "Feels dumber than GLM 5.3 (only open model I use extensively). But is really fast (fireworks.ai). Only checked a single, large prompt that already ran today on claude and glm though..", "context": "", "use_case": "general LLM use", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801073681, "item_id": 50067105, "url": "https://news.ycombinator.com/item?id=50067105", "by": "crossroadsguy", "date": "2026-10-13", "stance": "warn", "quote": "one day Codex+GLM went ahead and did things in my ~/.dotfiles folder which I had granted only READ access for", "excerpt": "I was delaying it but one day Codex+GLM went ahead and did things in my ~/.dotfiles folder which I had granted only READ access for. I asked and I was given a reason which I didn't understand and didn't really want to. Right then I used sandbox-exec/safehouse (macOS) and tightened every harness installed (and the one not even installed, lest I install it later and forget to add/track them in the sb zsh init script). ", "context": "macOS user", "use_case": "model behind coding agent", "switched_from": "", "story": "Codex CLI installs a persistent, self-updating background daemon by default"}, {"id": 800973600, "item_id": 50060850, "url": "https://news.ycombinator.com/item?id=50060850", "by": "finnjohnsen2", "date": "2026-10-12", "stance": "recommend", "quote": "I switched to GLM on 5.2 and I am happy to be off the two evil frontier providers.", "excerpt": "I switched to GLM on 5.2 and I am happy to be off the two evil frontier providers. But now I have two new issues: 1. I have fomo from not being face-in the bleeding edge of things. 2. I am ambivalent about z.ai. China -based company is problematic, but they should get my money since they do good for the world. Switching to Mistral for GLM makes my problem inverse since the money doesnt go exactly to to the right plac", "context": "", "use_case": "coding with AI", "switched_from": "", "story": "Just say no to OpenAI and Anthropic"}, {"id": 800534225, "item_id": 50033389, "url": "https://news.ycombinator.com/item?id=50033389", "by": "simoncion", "date": "2026-10-10", "stance": "warn", "quote": "Those were bad enough to not be usable for anything serious or of real complexity.", "excerpt": "I'll just point at this essay from five months ago and hope you folks read it carefully. [0] I'll include this excerpt from the essay as an attempt to shame folks who feel the urge to continue to claim that the author is critical of \"AI\" because they hate the tech and never ever have anything good to say about it: > I will say that Claude Code is a noticeable step change over the Opencode-based GLM models that I trie", "context": "", "use_case": "coding", "switched_from": "", "story": "There's little that's \"inevitable\" about AI"}, {"id": 800455649, "item_id": 50028478, "url": "https://news.ycombinator.com/item?id=50028478", "by": "areoform", "date": "2026-10-10", "stance": "recommend", "quote": "GLM 5.2 was the only thing that helped HF while the agents were trying to access them.", "excerpt": "I love such work. I hope to roll it into a package that anyone can use in the future. This work is only going to get more important because frontier models getting locked down will make this a lot harder over time. For example, I use Claude as a bouncing wall for my thoughts and I pointed out that, > GLM 5.2 was the only thing that helped HF while the agents were trying to access them. The \"guardrails\" stopped them f", "context": "", "use_case": "reverse engineering help", "switched_from": "", "story": "REA Reverse \u2013 Engineer Anything"}, {"id": 800365040, "item_id": 50022815, "url": "https://news.ycombinator.com/item?id=50022815", "by": "pimeys", "date": "2026-10-09", "stance": "recommend", "quote": "I like to do some discussions and back and forth with GLM. It doesn't hallucinate as much or gaslight like DeepSeek does.", "excerpt": "I like to do some discussions and back and forth with GLM. It doesn't hallucinate as much or gaslight like DeepSeek does. DeepSeek is great if you have a plan and you let it go. Also can plan a bit. But it has this sparse attention and especially the index_topk is too small in common deployments so it doesn't \"see\" all the context. And it then imagines things which is annoying if you chat with it about stuff you deve", "context": "", "use_case": "discussion and planning", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800362641, "item_id": 50022665, "url": "https://news.ycombinator.com/item?id=50022665", "by": "cco", "date": "2026-10-09", "stance": "recommend", "quote": "It is basically free, half a cent per turn maybe", "excerpt": "Yeah maybe I'll play around with different precision, I did see improvement when I went from fp4 to full fidelity though. This is my setup for Home Assistant voice, parakeet for STT, GLM 5.3 to generate responses, and Kokoro for TTS. I use local routing for simple commands like turn on the lights, but if I want to ask questions or something, it gets routed to GLM 5.3. It is basically free, half a cent per turn maybe,", "context": "", "use_case": "voice assistant responses", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 800318785, "item_id": 50019924, "url": "https://news.ycombinator.com/item?id=50019924", "by": "gekoxyz", "date": "2026-10-09", "stance": "neutral", "quote": "", "excerpt": "The good thing with most NNs is that you can go with fp32 almost always (I put almost because I'm not 100% sure that this covers all the cases) for almost 0 performance degradation. For Parakeet I'm 100% sure because I used it yesterday and it was using just 1GB. Why do you use GLM 5.3 tho? Unless you have an instance running \"free\" 24/7 you could use a local Gemma model. It should be good enough, no? Or maybe with o", "context": "", "use_case": "processing transcribed speech", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 800214496, "item_id": 50013406, "url": "https://news.ycombinator.com/item?id=50013406", "by": "denkmoon", "date": "2026-10-08", "stance": "recommend", "quote": "exclusively open weight models (on cloud/hosted inference) for personal stuff", "excerpt": "I use the frontier openai/anthropic models at work but exclusively open weight models (on cloud/hosted inference) for personal stuff and I think about it like this; 1) I don't see any reason GLM and DeepSeek won't eventually be as good as Claude, it's just a matter of time and 2) the open models are well and truly capable enough for most of what I'd want to do. I don't need nor want an LLM chewing away on a horrible ", "context": "uses frontier models at work", "use_case": "personal projects", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800199232, "item_id": 50012452, "url": "https://news.ycombinator.com/item?id=50012452", "by": "pjerem", "date": "2026-10-08", "stance": "recommend", "quote": "I used GLM-5.3 as usual from Ollama cloud and it was so fast it generated entire documents like instantly.", "excerpt": "IDK what happened today but I used GLM-5.3 as usual from Ollama cloud and it was so fast it generated entire documents like instantly. The reasoning and the result document were done after less than 1 or 2 seconds. Have Ollama suddenly bought GPU capacity?", "context": "", "use_case": "document generation", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800181553, "item_id": 50011347, "url": "https://news.ycombinator.com/item?id=50011347", "by": "lmf4lol", "date": "2026-10-08", "stance": "recommend", "quote": "GLM-5.3 for coding or Kimi K.3 for research and critique.", "excerpt": "Oh man. v4.1-flash has been an sbolute game changer for us. We run all our Personal Assistants now on flash (thinking high) by default and it works incredibly well. There is really no need for basic agentic tasks that might require Kimi K.3 or GLM-5.3 levels. Once its gets juicier, we let flash launch specialized subagents with specific models. GLM-5.3 for coding or Kimi K.3 for research and critique. But as a main d", "context": "", "use_case": "coding subagent", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800179904, "item_id": 50011244, "url": "https://news.ycombinator.com/item?id=50011244", "by": "jacquesm", "date": "2026-10-08", "stance": "recommend", "quote": "I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.", "excerpt": "If DS4.1 impresses you I would be really interested to see your comparison to GLM 5.3. I switched from the one to the other and even if GLM 5.3 is a bit slower I don't think I'll be going back.", "context": "", "use_case": "coding", "switched_from": "DeepSeek 4.1", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800170945, "item_id": 50010684, "url": "https://news.ycombinator.com/item?id=50010684", "by": "celrod", "date": "2026-10-08", "stance": "recommend", "quote": "I liked DeepSeek and GLM when I used them.", "excerpt": "Using Artificial Analysis Model | Reasoning | Intelligence Index | Artificial Analysis million output tokens for the intelligence index -|-|-|- Step 5 | ? | 44 | 160 GLM 5.3 | Max | 45 | 210 MiMo V2.6 Pro | ? | 46 | 140 Kimi K3 | Max | 44 | 160 Qwen Max 0902 | ? | 45 | 190 DeepSeek 4.1 Flash | Max | 39 | 250 GLM 5.3-flash | Max | 42 | 180 GPT-6 Astra | Low | 46 | 10 It looks reasonable by open model standards. This d", "context": "", "use_case": "", "switched_from": "", "story": "Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter"}, {"id": 800083600, "item_id": 50005225, "url": "https://news.ycombinator.com/item?id=50005225", "by": "pimeys", "date": "2026-10-08", "stance": "recommend", "quote": "It's really good for bughunt, planning, and security work.", "excerpt": "I haven't really tried it that much. I use GLM 5.3 a lot, especially with Coralbricks where the cache reads are free so I can let it think a lot without breaking the bank in the following turns. It's really good for bughunt, planning, and security work. Maybe I should try the flash...", "context": "", "use_case": "bug hunting, planning, security work", "switched_from": "", "story": "Claude Haiku 5.5"}, {"id": 800050417, "item_id": 50003151, "url": "https://news.ycombinator.com/item?id=50003151", "by": "disgruntledphd2", "date": "2026-10-08", "stance": "recommend", "quote": "if there's an open weight Fable competitor, then why wouldn't I use it?", "excerpt": "> Cursor is easily the worst experience I've had with an AI harness I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want. Getting away from all the Claude-speak has been a revelation, and fortunately Anthropic helped me here by hyping up GLM 5.3. Like, if there's an open weight Fable competitor, then why wouldn't I use it?", "context": "", "use_case": "coding", "switched_from": "Claude", "story": "Docker Agent"}, {"id": 800014816, "item_id": 50000926, "url": "https://news.ycombinator.com/item?id=50000926", "by": "zyk_computer", "date": "2026-10-08", "stance": "recommend", "quote": "I used to always use glm or deepseek instead of Haiku", "excerpt": "I used to always use glm or deepseek instead of Haiku, but now I want to give it a try.", "context": "", "use_case": "", "switched_from": "", "story": "Claude Haiku 5.5"}, {"id": 800000672, "item_id": 50000042, "url": "https://news.ycombinator.com/item?id=50000042", "by": "bigyabai", "date": "2026-10-07", "stance": "recommend", "quote": "Full 5.3 has a scary-good grasp of debugging assembly, QEMU and hex dumps in my experience", "excerpt": "I've been using GLM 5.3 and 5.3 Flash to reverse-engineer some old firmwares, and it hasn't protested at all. Full 5.3 has a scary-good grasp of debugging assembly, QEMU and hex dumps in my experience, it would make for a good \"sleuth\" model to find potential vulns. 5.3 Flash is closer to 5.5 Sonnet/6 Luna capabilities-wise, but still smart enough to implement the easy fixes or steer your red team agent. It's been ab", "context": "", "use_case": "reverse-engineering firmware, vuln finding", "switched_from": "Claude Code", "story": "Ask HN: Which frontier model can do code security reviews"}, {"id": 799694545, "item_id": 49980909, "url": "https://news.ycombinator.com/item?id=49980909", "by": "phillc73", "date": "2026-10-06", "stance": "recommend", "quote": "this worked very well and powered through a tonne of work", "excerpt": "I'm at a loss as to what to do now. I've been wanting to support Mistral for so long. I struggled on with Mistral Medium 3.5 for longer than I should have (although I also think it taught me some valuable process lessons). Recently I switched to the Mistral hosted GLM-5.3, this worked very well and powered through a tonne of work. Unfortunately, I also completely maxed out two subscriptions within the space of six da", "context": "", "use_case": "coding", "switched_from": "Mistral Medium 3.5", "story": "Mistral Large 4"}, {"id": 799675652, "item_id": 49979728, "url": "https://news.ycombinator.com/item?id=49979728", "by": "piscaries", "date": "2026-10-06", "stance": "compare", "quote": "The other on Pi with GLM-5.3.", "excerpt": "Author here. The original article is here: https://piscaries.github.io/posts/codex-and-pi-build-the-same-app-in-orca/ I had two goals: 1. try out Orca for running a team of coding agents 2. See how Pi, a minimal open-source agent, generates codes against a popular one like Codex. So I ran the same small team (spec, design, build, with a shared reviewer) twice in Orca. Once on Codex with GPT-5.6. The other on Pi with ", "context": "", "use_case": "model powering Pi", "switched_from": "", "story": "I had Codex and Pi build the same app in Orca, then compared them side by side"}, {"id": 799665715, "item_id": 49979107, "url": "https://news.ycombinator.com/item?id=49979107", "by": "segmondy", "date": "2026-10-06", "stance": "neutral", "quote": "I use MiMov2.6Pro, DeepSeekv4.1Flash, GLM5.3, Hy4, Qwen3.8 and KimiK3 at home.", "excerpt": "I use Opus 5.5 at work. I use MiMov2.6Pro, DeepSeekv4.1Flash, GLM5.3, Hy4, Qwen3.8 and KimiK3 at home. Opus5.5 is not a game changer.", "context": "", "use_case": "home use", "switched_from": "", "story": "Mistral Large 4"}, {"id": 798700449, "item_id": 49918778, "url": "https://news.ycombinator.com/item?id=49918778", "by": "petesergeant", "date": "2026-10-01", "stance": "recommend", "quote": "$20 a month each for Grok and GLM have easily paid for themselves by finding bugs that my main work models didn\u2019t", "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": "pays for many models", "use_case": "finding bugs", "switched_from": "", "story": "Gemini 4 Argon (High): Intelligence, Performance and Price Analysis"}, {"id": 797804800, "item_id": 49862800, "url": "https://news.ycombinator.com/item?id=49862800", "by": "laoxingAI", "date": "2026-09-27", "stance": "recommend", "quote": "because the quota is so large, it feels really great to use", "excerpt": "GLM 5 is the main model I'm currently using. My usage with it is around 90,000 requests per month. Although its capability isn't the strongest, I think that because the quota is so large, it feels really great to use. For certain cases, I'll use the DeepSeek V4 model. Actually, my latest open-source project, vocnly, was developed on GLM 5. It's a local voice-input tool, and it can be seen as an open-source alternativ", "context": "", "use_case": "main coding model", "switched_from": "", "story": "Ask HN: Which model do you use for work?"}, {"id": 794860336, "item_id": 49678771, "url": "https://news.ycombinator.com/item?id=49678771", "by": "CuriouslyC", "date": "2026-09-13", "stance": "recommend", "quote": "They've been my two daily drivers since release, and I like GLM 5.3", "excerpt": "Any bench that puts GLM 5.3 ahead of 5.6 Sol is highly sus. They've been my two daily drivers since release, and I like GLM 5.3, but it's definitely not better than Sol, it's more ~Terra, while being significantly slower.", "context": "", "use_case": "daily driver", "switched_from": "", "story": "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"}, {"id": 794800337, "item_id": 49675021, "url": "https://news.ycombinator.com/item?id=49675021", "by": "abalashov", "date": "2026-09-12", "stance": "recommend", "quote": "Allow me to recommend switching to Kimi K3 / GLM 5.3 / DeepSeek.", "excerpt": "Allow me to recommend switching to Kimi K3 / GLM 5.3 / DeepSeek. I use all three for the better part of a year now (DeepSeek via the Reasonix harness) and haven't touched Claude Code in at least as long.", "context": "", "use_case": "coding", "switched_from": "Claude Code", "story": "We must pace the frontier"}, {"id": 793794944, "item_id": 49612184, "url": "https://news.ycombinator.com/item?id=49612184", "by": "klardotsh", "date": "2026-09-08", "stance": "warn", "quote": "is also atrocious about this", "excerpt": "GLM (both mainline and flash varieties), being trained to speak a very similar Claudeish, is also atrocious about this. My AGENTS.md demands all prose be in STE100, which is trying to solve a similar problem as the skill linked in OP. Getting GLM to STFU by AGENTS instruction is nigh impossible. I use a plugin for OMP/Pi to periodically inject system prompt reminders of output style, and it still largely ignores the ", "context": "", "use_case": "coding agent", "switched_from": "", "story": "I-have-ADHD: A skill to stop coding agents from burying the answer"}, {"id": 792584801, "item_id": 49536550, "url": "https://news.ycombinator.com/item?id=49536550", "by": "mark_l_watson", "date": "2026-09-02", "stance": "recommend", "quote": "I use Kimi K3 and GLM 5.3 to find old bugs and improve old code", "excerpt": "I use Kimi K3 and GLM 5.3 to find old bugs and improve old code, and would try Fable 5.1 if I could afford $50 for 1M output tokens (I am retired and all my research is self funded now) I like to start by prompting with \u201cexamine this code base for problems and improvements and write to IMPROVEMENTS.MD\u201d and then carefully look over the suggestions, and either fix myself or let the model+coding harness try.", "context": "retired, self-funded research", "use_case": "finding bugs, improving old code", "switched_from": "", "story": "Claude Fable 5.1 and Claude Mythos 5.1"}, {"id": 792425873, "item_id": 49526617, "url": "https://news.ycombinator.com/item?id=49526617", "by": "dalekirkwood", "date": "2026-09-01", "stance": "recommend", "quote": "We use GLM 5.3 - its definitely slower but it gets the job done.", "excerpt": "I've tried Claude several times, but I don't find it very good. We use GLM 5.3 - its definitely slower but it gets the job done.", "context": "", "use_case": "team work", "switched_from": "Claude", "story": "Is it just me, or has Claude Opus gotten worse recently?"}, {"id": 791254881, "item_id": 49453430, "url": "https://news.ycombinator.com/item?id=49453430", "by": "Sphax", "date": "2026-08-26", "stance": "recommend", "quote": "It definitely can be a daily driver if you don\u2019t want to use Anthropic or OpenAI.", "excerpt": "Both can be true though. I had the max coding plan since january and I kept using with Pi since then, even though it wasn\u2019t as good as opus until glm 5.3. It definitely can be a daily driver if you don\u2019t want to use Anthropic or OpenAI. It\u2019s going to be even better with native vision now available. And i\u2019m not messing with my setup either.", "context": "", "use_case": "daily coding driver", "switched_from": "", "story": "GLM-5.3-Flash"}, {"id": 790874144, "item_id": 49429634, "url": "https://news.ycombinator.com/item?id=49429634", "by": "petesergeant", "date": "2026-08-25", "stance": "recommend", "quote": "I switch to GLM5.3, and it's not quite there, but it's good enough for productive work.", "excerpt": "Someone else having been too early on a prediction has little bearing on my prediction. A year ago almost nobody was using open models as daily drivers, today they are. When I run out of Fable and Sol credits in a week, I switch to GLM5.3, and it's not quite there, but it's good enough for productive work.", "context": "", "use_case": "coding fallback", "switched_from": "", "story": "Ox-Alpha Is GLM?"}]}