{"slug": "claude-sonnet", "name": "Claude Sonnet", "category": "ai", "category_name": "AI models and assistants", "description": "Anthropic's mid-tier large language model in the Claude family, balancing capability and cost.", "recommenders": 93, "commenters": 191, "warners": 22, "score": 80.256, "rising": -0.56, "first": "2025-11-04", "latest": "2026-10-31", "why": "HN commenters use Sonnet as a cheaper, good-enough workhorse for coding and routine API tasks, often having it implement while Opus plans.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 97, "neutral": 63, "compare": 19, "warn": 24}, "spark": [10, 3, 4, 5, 9, 7, 4, 14, 17, 9, 6, 9], "listed": true, "loved": ["Low cost", "Coding quality"], "caveat": "Weaker than Opus", "short_quote": "Sonnet 4.6 feels like a fundamentally different model than Sonnet 4.5, it is much closer to the Opus series in terms of agentic behavior and autonomy.", "icon": true, "domain": "anthropic.com", "github_repo": null, "official_url": "https://www.anthropic.com/claude/sonnet", "pricing": "paid", "aliases": ["Claude Sonnet", "Sonnet", "Sonnet 5", "Sonnet 4.5", "Claude Sonnet 4.5", "Claude Sonnet 4.6", "Sonnet 4.6", "Claude Sonnet 5", "Sonnet 5.5", "Claude 3.5 Sonnet", "Claude Sonnet 4", "Claude Sonnet 5.5", "Claude 4.5 Sonnet"], "verdict": [{"text": "HN commenters use Sonnet as a cheaper, good-enough workhorse for coding and routine API tasks,", "cites": [{"id": 784630992, "item_id": 49039437, "url": "https://news.ycombinator.com/item?id=49039437", "by": "plqbfbv", "date": "2026-07-24", "stance": "recommend", "quote": "I daily drive Sonnet 5/medium because it gets most things right most of the time at first try", "excerpt": "I daily drive Sonnet 5/medium because it gets most things right most of the time at first try, while costing a lot less than Fable. Opus can give better results on architectural/concept tasks and I use it sparingly, but it still costs more than Sonnet 5. Opus 5 seems to achieve results very close to Fable 5 while costing less (keeps Opus 4.8 pricing IIUC), but still more than Sonnet 5 then.", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Claude Opus 5"}, {"id": 798247904, "item_id": 49890494, "url": "https://news.ycombinator.com/item?id=49890494", "by": "randerson", "date": "2026-09-29", "stance": "recommend", "quote": "I use Sonnet in my actual application, because it is far cheaper at scale.", "excerpt": "While I mostly use Opus for coding, I use Sonnet in my actual application, because it is far cheaper at scale. I have Sonnet parse user free-text input, understand it and return the meaning as structured json. It doesn't need advanced reasoning, just a good enough understanding.", "context": "", "use_case": "parsing user text to JSON", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 803982528, "item_id": 50248908, "url": "https://news.ycombinator.com/item?id=50248908", "by": "notatoad", "date": "2026-10-26", "stance": "recommend", "quote": "for running routine api requests, sonnet is great.", "excerpt": "i use sonnet to generate answers to help-desk tickets, which it does for significantly cheaper and insignificantly worse than opus. if you're just talking about use in codex or claude code, then sure, leave it on opus all the time. but for running routine api requests, sonnet is great.", "context": "", "use_case": "answering help-desk tickets", "switched_from": "", "story": "GPT-6.1 Terra"}, {"id": 779829664, "item_id": 48739354, "url": "https://news.ycombinator.com/item?id=48739354", "by": "butterisgood", "date": "2026-06-30", "stance": "recommend", "quote": "I would use sonnet 5 for coding \u2026 seems alright!", "excerpt": "I used sonnet five today to evaluate work I\u2019m doing on an experimental programming language with an interesting concurrency model. I asked it to try to figure out why one of the examples wasn\u2019t working. It read the implementation of the compiler and the runtime, found the bug, fixed it, fixed the example and the only thing I had to do manually is suggest a less silly name for a particular function. I would use sonnet", "context": "working on an experimental programming language", "use_case": "debugging and fixing code", "switched_from": "", "story": "Claude Sonnet 5 \u2013 benchmark results"}, {"id": 794778960, "item_id": 49673685, "url": "https://news.ycombinator.com/item?id=49673685", "by": "seabrookmx", "date": "2026-09-12", "stance": "recommend", "quote": "Sonnet. It makes my token budget go further and I prefer to have the LLM churn away on rote work while I do the thinking.", "excerpt": "Sonnet. It makes my token budget go further and I prefer to have the LLM churn away on rote work while I do the thinking. So while Opus and Fable are undoubtedly smarter, that doesn't materially affect _my_ workflow. I'm not as up to date on the other vendors' models, but when I last used Gemini my feelings were similar between Pro and Flash.", "context": "", "use_case": "rote coding work", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}]}, {"text": " often having it implement while Opus plans.", "cites": [{"id": 797857217, "item_id": 49866076, "url": "https://news.ycombinator.com/item?id=49866076", "by": "slimebot80", "date": "2026-09-27", "stance": "recommend", "quote": "Sonnet is good and cheap for executing", "excerpt": "so I use \"opusplan\" mode bc Opus is more expensive and supposedly better at thinking, and Sonnet is good and cheap for executing.... Changing models still gives us a usage hit (right?) but that is outweighed by benefits? Plan mode is more about be rambling on while Opus detangles my thoughts.", "context": "", "use_case": "executing plans", "switched_from": "", "story": "Plan mode is dead"}, {"id": 780833731, "item_id": 48802108, "url": "https://news.ycombinator.com/item?id=48802108", "by": "schnitzelstoat", "date": "2026-07-06", "stance": "recommend", "quote": "I just use Opus for planning and Sonnet for implementation and it's pretty cheap", "excerpt": "My company has a Claude Code and Codex one and I use Claude Code because I am more familiar with it. That said, I just use Opus for planning and Sonnet for implementation and it's pretty cheap. Codex seems decent too so I should try it out some more. But you can get an awful lot done even with just like $200 a month at API pricing if you are careful not to waste a powerful model on an easy task, or carry around a blo", "context": "", "use_case": "implementation", "switched_from": "", "story": "When AI Costs More Than the Engineer"}, {"id": 785336720, "item_id": 49083545, "url": "https://news.ycombinator.com/item?id=49083545", "by": "oggreen", "date": "2026-07-28", "stance": "recommend", "quote": "I use Sonnet 80% of the time when I'm on claude.ai", "excerpt": "I use Sonnet 80% of the time when I'm on claude.ai and on Claude Code my main agent is Opus and typically my sub-agents are Sonnet. I use this setup mainly because I genuinely don't know if anything I'm doing is complex enough to need Fable and I don't want to run up my usage too much. It's basically like trying to kill a gnat with a sledgehammer. Hell, at work Haiku almost always works just as well as Sonnet does an", "context": "", "use_case": "everyday AI tasks and sub-agents", "switched_from": "", "story": "Why I prefer Opus 5 to Fable 5"}, {"id": 794800033, "item_id": 49675002, "url": "https://news.ycombinator.com/item?id=49675002", "by": "jakevoytko", "date": "2026-09-12", "stance": "recommend", "quote": "For well-defined coding tasks, I'd default to either Luna or Sonnet", "excerpt": "My workhorse is Opus orchestrating Sonnet or Sol orchestrating Luna, depending on which ecosystem I'm using this week. I'm a backend engineer, so for tasks that either interact with the machine learning or client codebases, I have Fable (Medium) review across the product spec, tech spec, and all the codebases after the implementation is done (haven't tried this workflow with Astra yet, don't know if it's a good revie", "context": "backend engineer", "use_case": "well-defined coding tasks", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}]}, {"text": " The most common complaints are that it reasons less carefully than Opus on harder work", "cites": [{"id": 798138641, "item_id": 49883665, "url": "https://news.ycombinator.com/item?id=49883665", "by": "yipinwong", "date": "2026-09-28", "stance": "warn", "quote": "Tried Sonnet 5.5 but worse than OPUS for thinking for sure", "excerpt": "Sticking with OPUS 5.5 for resume/STAR generation for me. Tried Sonnet 5.5 but worse than OPUS for thinking for sure, less error/inconsistency check. I used Opus 5.5 med vs. Sonnet 5.5 High on hermes with the same agent.md, and soul.md It's either Opus is smarter for sure, or Sonnet is ignoring my contexts. --- For those who downvoted my comment last week regarding using Opus 5.5 for resume, go get lost somewhere. I ", "context": "", "use_case": "resume/STAR generation", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 780031344, "item_id": 48751959, "url": "https://news.ycombinator.com/item?id=48751959", "by": "vlan121", "date": "2026-07-01", "stance": "warn", "quote": "Performance is worse than Opus 4.8", "excerpt": "Changelog: https://github.com/anthropics/claude-code/releases Performance is worse than Opus 4.8: https://www.anthropic.com/news/claude-sonnet-5", "context": "", "use_case": "", "switched_from": "", "story": "Claudes newest update is putting a worse model to default"}, {"id": 801571793, "item_id": 50098237, "url": "https://news.ycombinator.com/item?id=50098237", "by": "artyom", "date": "2026-10-15", "stance": "recommend", "quote": "Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry", "excerpt": "Second this. Since Opus 4.6 there's been a very noticeable bump in accuracy at just doing FreeCAD+Python or OpenSCAD code, usually one-shots things with basically described geometry. Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry Disclaimer: I use it for very precise 3D printing, not woodwork.", "context": "", "use_case": "generating CAD code", "switched_from": "", "story": "Ask HN: CAD for wood working with LLM support?"}, {"id": 786132336, "item_id": 49133271, "url": "https://news.ycombinator.com/item?id=49133271", "by": "aetherspawn", "date": "2026-08-01", "stance": "recommend", "quote": "try Sonnet 5, it has no guardrails and it can run continuously", "excerpt": "Yeah try Sonnet 5, it has no guardrails and it can run continuously. Hook it up to IDA, or I use Ghidra, with MCP and it can autonomously search for whatever you tell it to using a text prompt. It\u2019s way faster than doing it by hand. Only issue is Sonnet is kind of a silly model and whilst it\u2019s good at searching for stuff, it lacks a little bit of common sense compared to Opus or Fable, so you\u2019ll have to drive it. You", "context": "reverse engineer", "use_case": "autonomous reverse engineering", "switched_from": "", "story": "Twenty-five years ago it was cryptography, today it's model weights"}]}, {"text": " and that its quality feels inconsistent or degraded across releases.", "cites": [{"id": 804024528, "item_id": 50251533, "url": "https://news.ycombinator.com/item?id=50251533", "by": "lousken", "date": "2026-10-26", "stance": "warn", "quote": "sometimes it's dumber, sometimes it is smarter (mostly dumber though)", "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": 788762994, "item_id": 49297687, "url": "https://news.ycombinator.com/item?id=49297687", "by": "ilitirit", "date": "2026-08-14", "stance": "warn", "quote": "Sonnet isn't even worth considering in my world.", "excerpt": "I still haven't moved from Codex GPT5.5. Sonnet and Opus 5 have just been awful for my use cases. I recently caught Opus 5 hallucinating about code it just wrote. It's just not nearly as cost effective as GPT5.5, and it's too verbose, and it never \"has the full picture\". Sonnet isn't even worth considering in my world. Both recent models definitely feel nerfed.", "context": "", "use_case": "coding", "switched_from": "", "story": "Why does Opus 5 feel worse to work with?"}, {"id": 779895376, "item_id": 48743461, "url": "https://news.ycombinator.com/item?id=48743461", "by": "seviu", "date": "2026-07-01", "stance": "warn", "quote": "new Sonet is a dumbed down expensive model, which already falls behind GLM 5.2 and Kimi 2.7.", "excerpt": "This. I have been using anthropic and codex subs, on max. All this changed in June. We are clearly entering an era where we cannot rely on American models. As a solo developer I value reliability over performance. I cannot pay hundred of $, plus a lot of my private time figuring out how to properly use this technology, for it to be taken away within hours. On top of that, the intelligence is being dialed down. Sonet ", "context": "solo developer", "use_case": "coding", "switched_from": "", "story": "Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5"}, {"id": 796680512, "item_id": 49792532, "url": "https://news.ycombinator.com/item?id=49792532", "by": "reedlaw", "date": "2026-09-21", "stance": "warn", "quote": "Same experience with Sonnet on low effort.", "excerpt": "Same experience with Sonnet on low effort. It used be when I used a \"table_name/id\" format to reference a db record, it knew exactly how to find it using connected mcp tools. Today it failed 4/4 times (I tried the exact same prompt in 4 separate sessions and each time it replied \"I don't have access to [...]\"). On medium effort it got it right the first time.", "context": "", "use_case": "querying db records via MCP tools", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}]}], "praise": [{"label": "Low cost", "summary": "Commenters pick it because it costs far less than Opus or Fable for similar everyday results.", "quotes": [{"id": 798247904, "item_id": 49890494, "url": "https://news.ycombinator.com/item?id=49890494", "by": "randerson", "date": "2026-09-29", "stance": "recommend", "quote": "I use Sonnet in my actual application, because it is far cheaper at scale.", "excerpt": "While I mostly use Opus for coding, I use Sonnet in my actual application, because it is far cheaper at scale. I have Sonnet parse user free-text input, understand it and return the meaning as structured json. It doesn't need advanced reasoning, just a good enough understanding.", "context": "", "use_case": "parsing user text to JSON", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 784630992, "item_id": 49039437, "url": "https://news.ycombinator.com/item?id=49039437", "by": "plqbfbv", "date": "2026-07-24", "stance": "recommend", "quote": "I daily drive Sonnet 5/medium because it gets most things right most of the time at first try", "excerpt": "I daily drive Sonnet 5/medium because it gets most things right most of the time at first try, while costing a lot less than Fable. Opus can give better results on architectural/concept tasks and I use it sparingly, but it still costs more than Sonnet 5. Opus 5 seems to achieve results very close to Fable 5 while costing less (keeps Opus 4.8 pricing IIUC), but still more than Sonnet 5 then.", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Claude Opus 5"}, {"id": 780833731, "item_id": 48802108, "url": "https://news.ycombinator.com/item?id=48802108", "by": "schnitzelstoat", "date": "2026-07-06", "stance": "recommend", "quote": "I just use Opus for planning and Sonnet for implementation and it's pretty cheap", "excerpt": "My company has a Claude Code and Codex one and I use Claude Code because I am more familiar with it. That said, I just use Opus for planning and Sonnet for implementation and it's pretty cheap. Codex seems decent too so I should try it out some more. But you can get an awful lot done even with just like $200 a month at API pricing if you are careful not to waste a powerful model on an easy task, or carry around a blo", "context": "", "use_case": "implementation", "switched_from": "", "story": "When AI Costs More Than the Engineer"}]}, {"label": "Coding quality", "summary": "Several say it handles real coding tasks well, sometimes matching or beating older Opus versions.", "quotes": [{"id": 779829664, "item_id": 48739354, "url": "https://news.ycombinator.com/item?id=48739354", "by": "butterisgood", "date": "2026-06-30", "stance": "recommend", "quote": "I would use sonnet 5 for coding \u2026 seems alright!", "excerpt": "I used sonnet five today to evaluate work I\u2019m doing on an experimental programming language with an interesting concurrency model. I asked it to try to figure out why one of the examples wasn\u2019t working. It read the implementation of the compiler and the runtime, found the bug, fixed it, fixed the example and the only thing I had to do manually is suggest a less silly name for a particular function. I would use sonnet", "context": "working on an experimental programming language", "use_case": "debugging and fixing code", "switched_from": "", "story": "Claude Sonnet 5 \u2013 benchmark results"}, {"id": 788513408, "item_id": 49282088, "url": "https://news.ycombinator.com/item?id=49282088", "by": "pmontra", "date": "2026-08-12", "stance": "recommend", "quote": "Anyway, Sonnet is still doing a good job.", "excerpt": "Opus 5 is too verbose. I'm using Sonnet 5 on a large porting project and it's good. I switched from Opus 5 to Sonnet 5 on a project of another customer and I didn't notice a decrease in quality. I concede that it's very difficult to assess a difference in quality unless one uses both models on the same task and carefully compare the code, not the output in the terminal. I really don't have the time and the tokens for", "context": "Works on projects for customers", "use_case": "large porting project", "switched_from": "Opus 5", "story": "DeepSeek V4 Pro 0813"}, {"id": 783214224, "item_id": 48950889, "url": "https://news.ycombinator.com/item?id=48950889", "by": "ahsillyme", "date": "2026-07-17", "stance": "recommend", "quote": "Sonnet 5 is probably better than Opus 4.8 in many cases", "excerpt": "Sonnet 5 is probably better than Opus 4.8 in many cases -- you may want to try it; I now use only Fable and Sonnet unless the task is explicitly one where Opus can't de-scope and be lazy (e.g. replicating exactly a system as a coarse model to be used for refactoring-and-lowering, (model system in Idris) is the last thing I used Opus for because it had no choice but to stay on scope).", "context": "", "use_case": "general coding tasks", "switched_from": "Opus 4.8", "story": "Fable gone \u2013 Usage credits are required for this model"}]}, {"label": "Implementation tier", "summary": "It is commonly used as the executor or sub-agent under an Opus planner or orchestrator.", "quotes": [{"id": 797857217, "item_id": 49866076, "url": "https://news.ycombinator.com/item?id=49866076", "by": "slimebot80", "date": "2026-09-27", "stance": "recommend", "quote": "Sonnet is good and cheap for executing", "excerpt": "so I use \"opusplan\" mode bc Opus is more expensive and supposedly better at thinking, and Sonnet is good and cheap for executing.... Changing models still gives us a usage hit (right?) but that is outweighed by benefits? Plan mode is more about be rambling on while Opus detangles my thoughts.", "context": "", "use_case": "executing plans", "switched_from": "", "story": "Plan mode is dead"}, {"id": 785336720, "item_id": 49083545, "url": "https://news.ycombinator.com/item?id=49083545", "by": "oggreen", "date": "2026-07-28", "stance": "recommend", "quote": "I use Sonnet 80% of the time when I'm on claude.ai", "excerpt": "I use Sonnet 80% of the time when I'm on claude.ai and on Claude Code my main agent is Opus and typically my sub-agents are Sonnet. I use this setup mainly because I genuinely don't know if anything I'm doing is complex enough to need Fable and I don't want to run up my usage too much. It's basically like trying to kill a gnat with a sledgehammer. Hell, at work Haiku almost always works just as well as Sonnet does an", "context": "", "use_case": "everyday AI tasks and sub-agents", "switched_from": "", "story": "Why I prefer Opus 5 to Fable 5"}, {"id": 794800033, "item_id": 49675002, "url": "https://news.ycombinator.com/item?id=49675002", "by": "jakevoytko", "date": "2026-09-12", "stance": "recommend", "quote": "For well-defined coding tasks, I'd default to either Luna or Sonnet", "excerpt": "My workhorse is Opus orchestrating Sonnet or Sol orchestrating Luna, depending on which ecosystem I'm using this week. I'm a backend engineer, so for tasks that either interact with the machine learning or client codebases, I have Fable (Medium) review across the product spec, tech spec, and all the codebases after the implementation is done (haven't tried this workflow with Astra yet, don't know if it's a good revie", "context": "backend engineer", "use_case": "well-defined coding tasks", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}]}, {"label": "Writing", "summary": "Some prefer it for text generation, explanations and narration over Opus's verbose voice.", "quotes": [{"id": 791767296, "item_id": 49485456, "url": "https://news.ycombinator.com/item?id=49485456", "by": "jaggederest", "date": "2026-08-28", "stance": "recommend", "quote": "Sonnet 4.whatever, I think, actually does a superb job at text generation", "excerpt": "We used to use markov chain generators of various types to spit out absolute insanity, in the early years of the century, and this is all I ever wanted from LLMs. I bet if you used a slightly older model for your text generation, you'd get really clean output. Sonnet 4.whatever, I think, actually does a superb job at text generation, despite it being only an ok coding model.", "context": "", "use_case": "text generation", "switched_from": "", "story": "Aspirational Clownmaxxing and Joey's cadillac todo list"}, {"id": 790315874, "item_id": 49394742, "url": "https://news.ycombinator.com/item?id=49394742", "by": "preg_match", "date": "2026-08-21", "stance": "recommend", "quote": "Sonnet actually works better for this type of thing.", "excerpt": "I use Claude code for basically everything, since the harness is pretty complete. The online chat interface works fine too. For basic research I downgrade the model and effort. Smarter models are good at knowing when to web search rather than guess, but you should always specify \u201cdo a web search\u201d. The one caveat is opus has an absolutely awful voice. The way it writes is annoying and verbose. Sonnet actually works be", "context": "", "use_case": "research", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 784783056, "item_id": 49048941, "url": "https://news.ycombinator.com/item?id=49048941", "by": "firasd", "date": "2026-07-25", "stance": "recommend", "quote": "I have been using Sonnet to write some Youtube narrations and I think I've discovered a kind of value that is not 'AI slop'", "excerpt": "I think it depends on the context too. Dale Carnegie (in his famous Win Friends.. book) mentioned how it's annoying to receive letters that say Dictated But Not Read. So people don't want to read (for example) a twitter reply or email that's written on their behalf rather than their own thoughts When it comes to something like a LinkedIn post however who cares. Everyone uses AI cause the content itself is mercenary a", "context": "", "use_case": "writing YouTube narrations", "switched_from": "", "story": "The whole premise of checking for human writing is daft"}]}, {"label": "Reverse engineering", "summary": "Users report it works well for reverse engineering and security work when paired with tools.", "quotes": [{"id": 786132336, "item_id": 49133271, "url": "https://news.ycombinator.com/item?id=49133271", "by": "aetherspawn", "date": "2026-08-01", "stance": "recommend", "quote": "try Sonnet 5, it has no guardrails and it can run continuously", "excerpt": "Yeah try Sonnet 5, it has no guardrails and it can run continuously. Hook it up to IDA, or I use Ghidra, with MCP and it can autonomously search for whatever you tell it to using a text prompt. It\u2019s way faster than doing it by hand. Only issue is Sonnet is kind of a silly model and whilst it\u2019s good at searching for stuff, it lacks a little bit of common sense compared to Opus or Fable, so you\u2019ll have to drive it. You", "context": "reverse engineer", "use_case": "autonomous reverse engineering", "switched_from": "", "story": "Twenty-five years ago it was cryptography, today it's model weights"}, {"id": 779813808, "item_id": 48738363, "url": "https://news.ycombinator.com/item?id=48738363", "by": "OsrsNeedsf2P", "date": "2026-06-30", "stance": "recommend", "quote": "The cheaper tokens but sufficiently smart with hard verification makes it a perfect combo for the task", "excerpt": "Great timing. I just started using Claude Sonnet as a long term reverse engineering project[0] for a game I used to play as a kid. The cheaper tokens but sufficiently smart with hard verification makes it a perfect combo for the task [0] https://github.com/dginovker/BFME-Source-Code/", "context": "", "use_case": "reverse engineering a game", "switched_from": "", "story": "Claude Sonnet 5"}, {"id": 804627952, "item_id": 50289247, "url": "https://news.ycombinator.com/item?id=50289247", "by": "aiisjustanif", "date": "2026-10-29", "stance": "recommend", "quote": "I use Sonnet for Insider Threat investigations and detection engineering daily without issue.", "excerpt": "I\u2019m curious of the use case, I use Sonnet for Insider Threat investigations and detection engineering daily without issue.", "context": "security professional doing insider threat work", "use_case": "insider threat investigations, detection engineering", "switched_from": "", "story": "Why is this fingerprinting script creating bioweapons?"}]}, {"label": "Speed", "summary": "Commenters note it finishes tasks quickly and uses fewer tokens than comparable models.", "quotes": [{"id": 803903024, "item_id": 50243939, "url": "https://news.ycombinator.com/item?id=50243939", "by": "criley2", "date": "2026-10-26", "stance": "recommend", "quote": "Sonnet 5.5 medium, GLM 5.3 flash and Deepseek V4.1 flash 1017 are all in a similar space in capacity and price", "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": "home use, coding tasks", "switched_from": "", "story": "Anthropic S-1"}, {"id": 788038721, "item_id": 49252420, "url": "https://news.ycombinator.com/item?id=49252420", "by": "qudat", "date": "2026-08-10", "stance": "recommend", "quote": "I already don\u2019t bother with Opus and stick with sonnet med.", "excerpt": "> Or maybe models get so good that a 30B model is genuinely smart enough to do everything, so nobody really needs a model like Opus or Sol unless they\u2019re trying to solve the Reimann Hypothesis. I don\u2019t really buy this. Models can do frontier mathematical work today while still being not smart enough to refactor large codebases as well as me, so it\u2019s hard to imagine a world where I don\u2019t just want to use the smartest ", "context": "", "use_case": "coding, speed", "switched_from": "", "story": "No, local models will not win"}, {"id": 801083648, "item_id": 50067728, "url": "https://news.ycombinator.com/item?id=50067728", "by": "FreePalestine1", "date": "2026-10-13", "stance": "recommend", "quote": "Sonnet 5.5 does most aspects of my job better than me and faster than me.", "excerpt": "I'm gonna give you the benefit of the doubt and assume you haven't extensively used the latest models. You should really play around with them. Give Sonnet 5.5 / Opus 5.5 a shot if you haven't. I am not a shill, I do not work for any AI company, and I used to think like you. But I've come to terms with the fact that Sonnet 5.5 does most aspects of my job better than me and faster than me. It made a mistake? No proble", "context": "", "use_case": "day-to-day job work", "switched_from": "", "story": "AI is a tool and using it well takes skill"}]}], "caveats": [{"label": "Weaker than Opus", "summary": "Several find it worse than Opus at careful thinking, complex geometry and common sense.", "quotes": [{"id": 798138641, "item_id": 49883665, "url": "https://news.ycombinator.com/item?id=49883665", "by": "yipinwong", "date": "2026-09-28", "stance": "warn", "quote": "Tried Sonnet 5.5 but worse than OPUS for thinking for sure", "excerpt": "Sticking with OPUS 5.5 for resume/STAR generation for me. Tried Sonnet 5.5 but worse than OPUS for thinking for sure, less error/inconsistency check. I used Opus 5.5 med vs. Sonnet 5.5 High on hermes with the same agent.md, and soul.md It's either Opus is smarter for sure, or Sonnet is ignoring my contexts. --- For those who downvoted my comment last week regarding using Opus 5.5 for resume, go get lost somewhere. I ", "context": "", "use_case": "resume/STAR generation", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 801571793, "item_id": 50098237, "url": "https://news.ycombinator.com/item?id=50098237", "by": "artyom", "date": "2026-10-15", "stance": "recommend", "quote": "Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry", "excerpt": "Second this. Since Opus 4.6 there's been a very noticeable bump in accuracy at just doing FreeCAD+Python or OpenSCAD code, usually one-shots things with basically described geometry. Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry Disclaimer: I use it for very precise 3D printing, not woodwork.", "context": "", "use_case": "generating CAD code", "switched_from": "", "story": "Ask HN: CAD for wood working with LLM support?"}, {"id": 786132336, "item_id": 49133271, "url": "https://news.ycombinator.com/item?id=49133271", "by": "aetherspawn", "date": "2026-08-01", "stance": "recommend", "quote": "try Sonnet 5, it has no guardrails and it can run continuously", "excerpt": "Yeah try Sonnet 5, it has no guardrails and it can run continuously. Hook it up to IDA, or I use Ghidra, with MCP and it can autonomously search for whatever you tell it to using a text prompt. It\u2019s way faster than doing it by hand. Only issue is Sonnet is kind of a silly model and whilst it\u2019s good at searching for stuff, it lacks a little bit of common sense compared to Opus or Fable, so you\u2019ll have to drive it. You", "context": "reverse engineer", "use_case": "autonomous reverse engineering", "switched_from": "", "story": "Twenty-five years ago it was cryptography, today it's model weights"}]}, {"label": "Inconsistent quality", "summary": "Some say its quality varies or has been nerfed, especially at low effort settings.", "quotes": [{"id": 804024528, "item_id": 50251533, "url": "https://news.ycombinator.com/item?id=50251533", "by": "lousken", "date": "2026-10-26", "stance": "warn", "quote": "sometimes it's dumber, sometimes it is smarter (mostly dumber though)", "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": 796680512, "item_id": 49792532, "url": "https://news.ycombinator.com/item?id=49792532", "by": "reedlaw", "date": "2026-09-21", "stance": "warn", "quote": "Same experience with Sonnet on low effort.", "excerpt": "Same experience with Sonnet on low effort. It used be when I used a \"table_name/id\" format to reference a db record, it knew exactly how to find it using connected mcp tools. Today it failed 4/4 times (I tried the exact same prompt in 4 separate sessions and each time it replied \"I don't have access to [...]\"). On medium effort it got it right the first time.", "context": "", "use_case": "querying db records via MCP tools", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}, {"id": 788762994, "item_id": 49297687, "url": "https://news.ycombinator.com/item?id=49297687", "by": "ilitirit", "date": "2026-08-14", "stance": "warn", "quote": "Sonnet isn't even worth considering in my world.", "excerpt": "I still haven't moved from Codex GPT5.5. Sonnet and Opus 5 have just been awful for my use cases. I recently caught Opus 5 hallucinating about code it just wrote. It's just not nearly as cost effective as GPT5.5, and it's too verbose, and it never \"has the full picture\". Sonnet isn't even worth considering in my world. Both recent models definitely feel nerfed.", "context": "", "use_case": "coding", "switched_from": "", "story": "Why does Opus 5 feel worse to work with?"}]}, {"label": "Hard to steer", "summary": "Users report it can go on tangents, over-comment, or overdo agentic tasks despite instructions.", "quotes": [{"id": 794123634, "item_id": 49632727, "url": "https://news.ycombinator.com/item?id=49632727", "by": "surgical_fire", "date": "2026-09-09", "stance": "warn", "quote": "I honestly have more issues steering Sonnet properly.", "excerpt": "I used a lot V4 flash to implement plans built by other models, and it was honestly top notch. The thing was a workhorse, and I got none of the isuses you describe. I was mostly using DeepSeek on Pi, connecting to their API directly (not some third party provider). I honestly have more issues steering Sonnet properly.", "context": "", "use_case": "coding", "switched_from": "", "story": "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"}, {"id": 790476817, "item_id": 49404801, "url": "https://news.ycombinator.com/item?id=49404801", "by": "ricardobeat", "date": "2026-08-22", "stance": "warn", "quote": "Same seems to be true for Sonnet 5.", "excerpt": "I use Opus 5 almost exclusively at low effort, and get good results. Especially on high it seems to go out on completely unasked-for tangents. Same seems to be true for Sonnet 5. Older models did not behave like this. The mood change in just six months is wild, in February this year Claude was the most liked LLM by far.", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic appears to be A/B testing reduced effort levels in Claude Code"}, {"id": 779789329, "item_id": 48736833, "url": "https://news.ycombinator.com/item?id=48736833", "by": "microtonal", "date": "2026-06-30", "stance": "warn", "quote": "This announcement does not make me positive, I have found that the more models are optimized for fully agentic development, the worse they get at assisted development", "excerpt": "Claude Sonnet 5 is built to be the most agentic Sonnet model yet. It can make plans, use tools like browsers and terminals, and run autonomously at a level that, just a few months ago, required larger and more expensive models. I have been using Sonnet 4.6 more than Opus, because I'm mostly doing agent-assisted development and not fully agent-driven development. This announcement does not make me positive, I have fou", "context": "", "use_case": "", "switched_from": "", "story": "Claude Sonnet 5"}]}, {"label": "Cost of newer versions", "summary": "A few say newer Sonnet releases are pricier and lose to cheaper open models.", "quotes": [{"id": 791780435, "item_id": 49486277, "url": "https://news.ycombinator.com/item?id=49486277", "by": "charrondev", "date": "2026-08-29", "stance": "warn", "quote": "the newer models are a lot more expensive at the per-token pricing", "excerpt": "I used cursor extensively both at work and for personal use. Its harness is pretty darn good but I basically never used OpenAI models in it. The first party cursor models (initially composer and now grok-cursor) and price very competitively for their quality and have very generous usage limits included in the base plans, and then per token pricing afterwards. Occasionally I\u2019ve used some of the Anthropic models in it ", "context": "", "use_case": "coding in Cursor", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 779895376, "item_id": 48743461, "url": "https://news.ycombinator.com/item?id=48743461", "by": "seviu", "date": "2026-07-01", "stance": "warn", "quote": "new Sonet is a dumbed down expensive model, which already falls behind GLM 5.2 and Kimi 2.7.", "excerpt": "This. I have been using anthropic and codex subs, on max. All this changed in June. We are clearly entering an era where we cannot rely on American models. As a solo developer I value reliability over performance. I cannot pay hundred of $, plus a lot of my private time figuring out how to properly use this technology, for it to be taken away within hours. On top of that, the intelligence is being dialed down. Sonet ", "context": "solo developer", "use_case": "coding", "switched_from": "", "story": "Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5"}, {"id": 780040418, "item_id": 48752526, "url": "https://news.ycombinator.com/item?id=48752526", "by": "InsideOutSanta", "date": "2026-07-01", "stance": "warn", "quote": "I don't think there's much reason to ever use Sonnet for anything if you can use GLM 5.2 instead.", "excerpt": "It's comparable, but not the same. For some tasks, it's better. Opus refuses tasks for me pretty regularly. GLM 5.2 has never refused a task. So for anything security-related or that touches on topics that trigger Opus's safety guardrails, I use GLM 5.2. OTOH, for anything related to UI design, I use Opus 4.8. It's much better at taking relatively vague descriptions of user interfaces and a mockup of a related UI and", "context": "", "use_case": "", "switched_from": "", "story": "ZCode: Claude Code from the Makers of GLM"}]}, {"label": "Refusals", "summary": "One commenter hit a new refusal to enter credentials through a browser MCP.", "quotes": [{"id": 780057089, "item_id": 48753568, "url": "https://news.ycombinator.com/item?id=48753568", "by": "madamelic", "date": "2026-07-01", "stance": "warn", "quote": "it told me that it can't do that because it violates its security protocol.", "excerpt": "Today I told Sonnet (!) to use a browser MCP to enter a username and password for the project it is working on, it told me that it can't do that because it violates its security protocol. This worked fine before. I love Claude, I have stuck with it even through people saying Codex is better but this is definitely getting to be the last straw. It's completely absurd I am paying them $200+ per month along with pushing ", "context": "", "use_case": "browser MCP automation", "switched_from": "", "story": "Fable 5 Is Back"}]}, {"label": "Hallucinations", "summary": "One commenter ranks it in a tier prone to hallucinated output.", "quotes": [{"id": 785947717, "item_id": 49121732, "url": "https://news.ycombinator.com/item?id=49121732", "by": "user43928", "date": "2026-07-31", "stance": "warn", "quote": "\"I love hallucinated garbage\": Sonnet, Qwen 3.6, GPT 5.4 mini, GPT 5.3 Codex", "excerpt": "In my mind there are three tiers: The SOTA: Fable, GPT 5.6 Sol, Opus 5 The \"enterprise admin did not turn on the new models\": Opus 4.8, GPT 5.5 The \"I love hallucinated garbage\": Sonnet, Qwen 3.6, GPT 5.4 mini, GPT 5.3 Codex, etc. Results vary widely", "context": "", "use_case": "", "switched_from": "", "story": "Google fixed more Chrome bugs in June than over the past two years, thanks to AI"}]}], "who": [{"by": "aiisjustanif", "context": "security professional doing insider threat work", "url": "https://news.ycombinator.com/item?id=50289247", "date": "2026-10-29"}, {"by": "Roark66", "context": "team with custom LLM review workflow", "url": "https://news.ycombinator.com/item?id=50260800", "date": "2026-10-27"}, {"by": "boogiefromzk", "context": "built an agentic delegation scheme", "url": "https://news.ycombinator.com/item?id=50251451", "date": "2026-10-26"}, {"by": "jakevoytko", "context": "backend engineer", "url": "https://news.ycombinator.com/item?id=49675002", "date": "2026-09-12"}, {"by": "mikeushakov", "context": "PhD candidate in social sciences", "url": "https://news.ycombinator.com/item?id=49509661", "date": "2026-08-31"}, {"by": "ianmarcinkowski", "context": "dev on a team of 4", "url": "https://news.ycombinator.com/item?id=49473310", "date": "2026-08-28"}, {"by": "naniel", "context": "team that breaks tasks down granularly", "url": "https://news.ycombinator.com/item?id=49448300", "date": "2026-08-26"}, {"by": "Bender", "context": "non-developer hobbyist", "url": "https://news.ycombinator.com/item?id=49427516", "date": "2026-08-25"}, {"by": "pmontra", "context": "Works on projects for customers", "url": "https://news.ycombinator.com/item?id=49282088", "date": "2026-08-12"}, {"by": "aetherspawn", "context": "reverse engineer", "url": "https://news.ycombinator.com/item?id=49133271", "date": "2026-08-01"}, {"by": "apsurd", "context": "professional developer", "url": "https://news.ycombinator.com/item?id=49112891", "date": "2026-07-30"}, {"by": "runjake", "context": "on multiple $20 plans", "url": "https://news.ycombinator.com/item?id=49111328", "date": "2026-07-30"}], "tags": ["for coding", "for routine API tasks", "for sub-agents", "for reverse engineering", "for writing"], "use_cases": ["coding", "ai coding", "agentic coding", "executing plans", "coding tasks", "coding assistance"], "compared": [{"slug": "claude-opus", "name": "Claude Opus", "co": 135, "switched_from": 6, "switched_to": 9}, {"slug": "claude-code", "name": "Claude Code", "co": 40, "switched_from": 0, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 31, "switched_from": 0, "switched_to": 3}, {"slug": "claude-fable", "name": "Claude Fable", "co": 33, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-5", "name": "GPT-5", "co": 23, "switched_from": 2, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 24, "switched_from": 0, "switched_to": 0}, {"slug": "gemini", "name": "Gemini", "co": 23, "switched_from": 0, "switched_to": 0}, {"slug": "claude-haiku", "name": "Claude Haiku", "co": 21, "switched_from": 1, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49672966", "title": "Ask HN: What default model do you use and why?", "mentions": 8}, {"url": "https://news.ycombinator.com/item?id=48736605", "title": "Claude Sonnet 5", "mentions": 5}, {"url": "https://news.ycombinator.com/item?id=46037637", "title": "Claude Opus 4.5", "mentions": 5}, {"url": "https://news.ycombinator.com/item?id=47919623", "title": "Ask HN: Can you tell the difference between Claude Sonnet and Opus?", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=49881850", "title": "Sonnet 5.5", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49038433", "title": "Claude Opus 5", "mentions": 3}], "sentiment_by_month": {"2025-11": {"recommend": 10, "compare": 1, "neutral": 4, "warn": 4}, "2025-12": {"recommend": 3, "neutral": 3, "warn": 1}, "2026-01": {"recommend": 4, "neutral": 1}, "2026-02": {"recommend": 5, "compare": 2, "neutral": 2}, "2026-03": {"recommend": 9, "neutral": 2, "warn": 2}, "2026-04": {"neutral": 6, "compare": 2, "warn": 1, "recommend": 7}, "2026-05": {"compare": 1, "recommend": 4, "neutral": 2}, "2026-06": {"neutral": 11, "recommend": 14, "compare": 4, "warn": 3}, "2026-07": {"warn": 6, "recommend": 17, "neutral": 9, "compare": 4}, "2026-08": {"recommend": 9, "compare": 1, "neutral": 7, "warn": 3}, "2026-09": {"neutral": 14, "compare": 2, "recommend": 6, "warn": 3}, "2026-10": {"compare": 2, "recommend": 9, "neutral": 2, "warn": 1}}, "quotes": [{"id": 805124434, "item_id": 50320277, "url": "https://news.ycombinator.com/item?id=50320277", "by": "gambiting", "date": "2026-10-31", "stance": "compare", "quote": "as good as or better than Sonnet", "excerpt": "GLM 5.3 Flash is incredibly cheap and imho as good as or better than Sonnet. I used it recently to fix an old server that my family had running serving some websites, and by fix it I mean I got it to log in over ssh, figure out what's running there, copy it out, log in to a brand new droplet on DO, set up a fresh instance of apache with everything patched up to latest, copy that ancient content over, make sure it run", "context": "", "use_case": "", "switched_from": "", "story": "HackerTube: YouTube built from videos recommended by HN"}, {"id": 804993475, "item_id": 50312092, "url": "https://news.ycombinator.com/item?id=50312092", "by": "CharlieDigital", "date": "2026-10-31", "stance": "compare", "quote": "Opus/Sonnet 5.5 driving the orchestrator", "excerpt": "I genuinely prefer OpenAI models for coding and building in general. My observation: GPT models are generally better at following the system prompt, tool use, and skill use. I use Paseo and there is a noticeable difference when GPT-6.1 Sol is driving the orchestrator vs Opus/Sonnet 5.5 driving the orchestrator. Anthropic models ignore the shared system prompt to use the Paseo tools for sub-agents and prefer to use it", "context": "", "use_case": "orchestrating agents", "switched_from": "", "story": "Anthropic to receive high 'junk' rating from credit agencies following IPO"}, {"id": 804627952, "item_id": 50289247, "url": "https://news.ycombinator.com/item?id=50289247", "by": "aiisjustanif", "date": "2026-10-29", "stance": "recommend", "quote": "I use Sonnet for Insider Threat investigations and detection engineering daily without issue.", "excerpt": "I\u2019m curious of the use case, I use Sonnet for Insider Threat investigations and detection engineering daily without issue.", "context": "security professional doing insider threat work", "use_case": "insider threat investigations, detection engineering", "switched_from": "", "story": "Why is this fingerprinting script creating bioweapons?"}, {"id": 804172802, "item_id": 50260800, "url": "https://news.ycombinator.com/item?id=50260800", "by": "Roark66", "date": "2026-10-27", "stance": "recommend", "quote": "runs opus or sonet (depending on complexity) to do a review", "excerpt": "Same here.LLMs are really good at code review providing they are configured correctly and have right docs and prompts. Github copilot review is s great example of the worst possible way this can be misused. It is the worst waste of tokens there is. Instead we use a process we created ourselves that runs opus or sonet (depending on complexity) to do a review (taking into account pr description and comments - copilot i", "context": "team with custom LLM review workflow", "use_case": "PR code review", "switched_from": "GitHub Copilot", "story": "I will no longer upload to NEW"}, {"id": 804024528, "item_id": 50251533, "url": "https://news.ycombinator.com/item?id=50251533", "by": "lousken", "date": "2026-10-26", "stance": "warn", "quote": "sometimes it's dumber, sometimes it is smarter (mostly dumber though)", "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": 804023217, "item_id": 50251451, "url": "https://news.ycombinator.com/item?id=50251451", "by": "boogiefromzk", "date": "2026-10-26", "stance": "recommend", "quote": "most context intensive work is done by Sonnet", "excerpt": "Last months I was searching for a way to make smart AI model submit and verify the work to cheap model so that it will cost less, and after many try and failures I was able to get stable result where I use Fable and its limits spent slower than overall account limit because most context intensive work is done by Sonnet. At the same time the response quaility is still Fable. I also made sure Opus controls Grok in Curs", "context": "built an agentic delegation scheme", "use_case": "context-intensive delegated work", "switched_from": "", "story": "Cost-effective agentic delegation scheme for Claude Code, Cursor and Codex"}, {"id": 803982528, "item_id": 50248908, "url": "https://news.ycombinator.com/item?id=50248908", "by": "notatoad", "date": "2026-10-26", "stance": "recommend", "quote": "for running routine api requests, sonnet is great.", "excerpt": "i use sonnet to generate answers to help-desk tickets, which it does for significantly cheaper and insignificantly worse than opus. if you're just talking about use in codex or claude code, then sure, leave it on opus all the time. but for running routine api requests, sonnet is great.", "context": "", "use_case": "answering help-desk tickets", "switched_from": "", "story": "GPT-6.1 Terra"}, {"id": 803903024, "item_id": 50243939, "url": "https://news.ycombinator.com/item?id=50243939", "by": "criley2", "date": "2026-10-26", "stance": "recommend", "quote": "Sonnet 5.5 medium, GLM 5.3 flash and Deepseek V4.1 flash 1017 are all in a similar space in capacity and price", "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": "home use, coding tasks", "switched_from": "", "story": "Anthropic S-1"}, {"id": 803825188, "item_id": 50239074, "url": "https://news.ycombinator.com/item?id=50239074", "by": "bitexploder", "date": "2026-10-26", "stance": "neutral", "quote": "It is about as reliable as Sonnet 5 for agentic coding.", "excerpt": "I mean, I just have 4xV100S GPU and a Macbook Pro w/48GB of RAM and I find it kind of amazing. My server can run Qwen Flash Next at 500 t/s aggregate (about 200 t/s single user). It's pretty great. I use it for local coding and all my worker agents. It is about as reliable as Sonnet 5 for agentic coding. I make 3D models, keep the home network and server updated, fully built ansible files. You do NOT need 20K in hard", "context": "", "use_case": "agentic coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 803390032, "item_id": 50211877, "url": "https://news.ycombinator.com/item?id=50211877", "by": "janandonly", "date": "2026-10-23", "stance": "neutral", "quote": "Normally I use Sonnnet or Opus on the Normal setting which is fine.", "excerpt": "I crossed my limit too this week. It was because I set Opus to Max by accident. Normally I use Sonnnet or Opus on the Normal setting which is fine.", "context": "", "use_case": "coding", "switched_from": "", "story": "Ask HN: Claude gets over my 5h limit today in 10 minutes?"}, {"id": 802763591, "item_id": 50172724, "url": "https://news.ycombinator.com/item?id=50172724", "by": "CharlieDigital", "date": "2026-10-20", "stance": "recommend", "quote": "One \"Principal Engineer\" Sonnet 5.5 or 6.1 Sol for some tasks.", "excerpt": "I use the frontier models only in plan mode; coding is held out to cheaper models. I run Paseo as an orchestrator with agent profiles. \"Distinguished Member of Technical Staff\" -> Fable, plan mode. \"End-User Customer Advocate\" -> Astra, plan mode. A few others. Basically, these agents (with profile prompts) can only be \"consulted\" for input on design elements; it's OK if they produce a bit of verbosity here. This has", "context": "", "use_case": "principal engineer agent", "switched_from": "", "story": "SlopCodeBench 10/2026 \u2013 Opus 5.5, Astra wins overall, xhigh considered harmful"}, {"id": 802160480, "item_id": 50135030, "url": "https://news.ycombinator.com/item?id=50135030", "by": "abalgir", "date": "2026-10-17", "stance": "recommend", "quote": "if I code with Claude (usually Sonnet 5.5-medium), Codex reviews it, and vice versa", "excerpt": "I agree with you. A code reviewer from the same company, even with different models or efforts, shares the same blind spots. To review my code, I use a different company; if I code with Claude (usually Sonnet 5.5-medium), Codex reviews it, and vice versa. I get much better code this way. But more importantly, I always tell the reviewer to build its own test-scenario ledger and refute the coder's claim that it is done", "context": "", "use_case": "coding, cross-reviewed by Codex", "switched_from": "", "story": "How the Claude Code team does code review"}, {"id": 801571793, "item_id": 50098237, "url": "https://news.ycombinator.com/item?id=50098237", "by": "artyom", "date": "2026-10-15", "stance": "recommend", "quote": "Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry", "excerpt": "Second this. Since Opus 4.6 there's been a very noticeable bump in accuracy at just doing FreeCAD+Python or OpenSCAD code, usually one-shots things with basically described geometry. Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry Disclaimer: I use it for very precise 3D printing, not woodwork.", "context": "", "use_case": "generating CAD code", "switched_from": "", "story": "Ask HN: CAD for wood working with LLM support?"}, {"id": 801083648, "item_id": 50067728, "url": "https://news.ycombinator.com/item?id=50067728", "by": "FreePalestine1", "date": "2026-10-13", "stance": "recommend", "quote": "Sonnet 5.5 does most aspects of my job better than me and faster than me.", "excerpt": "I'm gonna give you the benefit of the doubt and assume you haven't extensively used the latest models. You should really play around with them. Give Sonnet 5.5 / Opus 5.5 a shot if you haven't. I am not a shill, I do not work for any AI company, and I used to think like you. But I've come to terms with the fact that Sonnet 5.5 does most aspects of my job better than me and faster than me. It made a mistake? No proble", "context": "", "use_case": "day-to-day job work", "switched_from": "", "story": "AI is a tool and using it well takes skill"}, {"id": 800303169, "item_id": 50018948, "url": "https://news.ycombinator.com/item?id=50018948", "by": "joshstrange", "date": "2026-10-09", "stance": "compare", "quote": "it costs ~1/3rd Sonnet per task/PR according to my tracking", "excerpt": "I\u2019ve played with DS4.1 Flash. It\u2019s neat, no doubt. In my tests it does decently well against Sonnet 5.5 but uses way more tokens. That works out since it costs ~1/3rd Sonnet per task/PR according to my tracking. However, I can easily burn ~$5/day if I use it as my \u201cworker\u201d (still using opus for planning and review) so call it ~$150/mo. I could, if I were so inclined, get a second Claude Sub and have even more headroo", "context": "", "use_case": "coding tasks", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 798569555, "item_id": 49910597, "url": "https://news.ycombinator.com/item?id=49910597", "by": "gertlabs", "date": "2026-09-30", "stance": "compare", "quote": "6.1-Sol is also cheaper than Sonnet 5.5 and much smarter.", "excerpt": "We tested it across 100 unsaturated coding and engineering environments. Both Astra and 6.1-Sol are pretty comfortably ahead of Opus 5.5 in these types of evaluations, and both end up being cheaper than Opus via API usage. 6.1-Sol is also cheaper than Sonnet 5.5 and much smarter. The only verifiable domain Anthropic seems to be clearly ahead is chemistry (and perhaps also some unverifiable domains like being pleasant", "context": "", "use_case": "coding", "switched_from": "", "story": "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"}, {"id": 798398944, "item_id": 49899934, "url": "https://news.ycombinator.com/item?id=49899934", "by": "sanex", "date": "2026-09-29", "stance": "neutral", "quote": "My main who is either a sonnet or opus", "excerpt": "Yeah personally I use 3 levels of agents. My main who is either a sonnet or opus, he delegates complicated things to a project lead which is usually fable, and then he delegates everything to the dumbest possible model for the task.", "context": "", "use_case": "main agent", "switched_from": "", "story": "Dots: Always-on agents"}, {"id": 798247904, "item_id": 49890494, "url": "https://news.ycombinator.com/item?id=49890494", "by": "randerson", "date": "2026-09-29", "stance": "recommend", "quote": "I use Sonnet in my actual application, because it is far cheaper at scale.", "excerpt": "While I mostly use Opus for coding, I use Sonnet in my actual application, because it is far cheaper at scale. I have Sonnet parse user free-text input, understand it and return the meaning as structured json. It doesn't need advanced reasoning, just a good enough understanding.", "context": "", "use_case": "parsing user text to JSON", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 798161392, "item_id": 49885087, "url": "https://news.ycombinator.com/item?id=49885087", "by": "saint-evan", "date": "2026-09-28", "stance": "recommend", "quote": "I love Sonnet so much. Loved it since 3.5", "excerpt": "unwittingly said 'yaaay' when I saw the Sonnet 5.5 entry. lol I love Sonnet so much. Loved it since 3.5 and never really liked Opus even when I tried to use it for technical work. Once we had two back to back anthropic releases neither of which was a Sonnet upgrade from 4.5 (4.6?) and I was getting kinda sad that they're considering discontinuing it. These are weird reactions I'm having to these tools even when I mos", "context": "", "use_case": "technical work", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 798138641, "item_id": 49883665, "url": "https://news.ycombinator.com/item?id=49883665", "by": "yipinwong", "date": "2026-09-28", "stance": "warn", "quote": "Tried Sonnet 5.5 but worse than OPUS for thinking for sure", "excerpt": "Sticking with OPUS 5.5 for resume/STAR generation for me. Tried Sonnet 5.5 but worse than OPUS for thinking for sure, less error/inconsistency check. I used Opus 5.5 med vs. Sonnet 5.5 High on hermes with the same agent.md, and soul.md It's either Opus is smarter for sure, or Sonnet is ignoring my contexts. --- For those who downvoted my comment last week regarding using Opus 5.5 for resume, go get lost somewhere. I ", "context": "", "use_case": "resume/STAR generation", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 797896769, "item_id": 49868548, "url": "https://news.ycombinator.com/item?id=49868548", "by": "nikhilkxmar", "date": "2026-09-27", "stance": "neutral", "quote": "for the rest of the stuff I use sonnet 5 / gpt luna", "excerpt": "I usually use Opus 5.5 for coding stuff and for the rest of the stuff I use sonnet 5 / gpt luna doesn't really matter", "context": "", "use_case": "general tasks", "switched_from": "", "story": "Ask HN: Which model do you use for work?"}, {"id": 797857217, "item_id": 49866076, "url": "https://news.ycombinator.com/item?id=49866076", "by": "slimebot80", "date": "2026-09-27", "stance": "recommend", "quote": "Sonnet is good and cheap for executing", "excerpt": "so I use \"opusplan\" mode bc Opus is more expensive and supposedly better at thinking, and Sonnet is good and cheap for executing.... Changing models still gives us a usage hit (right?) but that is outweighed by benefits? Plan mode is more about be rambling on while Opus detangles my thoughts.", "context": "", "use_case": "executing plans", "switched_from": "", "story": "Plan mode is dead"}, {"id": 797828305, "item_id": 49864269, "url": "https://news.ycombinator.com/item?id=49864269", "by": "nibbleyou", "date": "2026-09-27", "stance": "neutral", "quote": "Sonnet sometimes if it is a simple task.", "excerpt": "Do you use luna to plan as well, or is it just code? I am interesting in understanding the process you follow. My workflow is the most common one - use something like Opus to help create a spec document (I decide the specs and then get the LLM to ask me questions to harden it), then generate a plan, and then implement. I use Opus the whole time. Sonnet sometimes if it is a simple task.", "context": "", "use_case": "simple coding tasks", "switched_from": "", "story": "How to keep enjoying programming in a world of LLMs"}, {"id": 796972144, "item_id": 49810759, "url": "https://news.ycombinator.com/item?id=49810759", "by": "sieve", "date": "2026-09-23", "stance": "neutral", "quote": "I use Claude Sonnet and ChatGPT via the web UI.", "excerpt": "I use Claude Sonnet and ChatGPT via the web UI. I often use Claude to come up with specs for my ideas. This is becoming less and less useful. DS4/MS13/MiMo are almost there for these use cases as well. I dogfood everything I produce, and the models are good at collaborating with me on a spec and then turning it into code. If Sonnet/ChatGPT suddenly became unavailable due to Anthropic/OpenAI suddenly not being able to", "context": "", "use_case": "specs for ideas", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 796942498, "item_id": 49808906, "url": "https://news.ycombinator.com/item?id=49808906", "by": "system2", "date": "2026-09-22", "stance": "neutral", "quote": "For censored stuff, we use Sonnet and OpenAI Nano models.", "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": "censored data processing", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 796680512, "item_id": 49792532, "url": "https://news.ycombinator.com/item?id=49792532", "by": "reedlaw", "date": "2026-09-21", "stance": "warn", "quote": "Same experience with Sonnet on low effort.", "excerpt": "Same experience with Sonnet on low effort. It used be when I used a \"table_name/id\" format to reference a db record, it knew exactly how to find it using connected mcp tools. Today it failed 4/4 times (I tried the exact same prompt in 4 separate sessions and each time it replied \"I don't have access to [...]\"). On medium effort it got it right the first time.", "context": "", "use_case": "querying db records via MCP tools", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}, {"id": 796649105, "item_id": 49790569, "url": "https://news.ycombinator.com/item?id=49790569", "by": "varispeed", "date": "2026-09-21", "stance": "neutral", "quote": "It's worse than Sonnet", "excerpt": "I stopped using Fable long time ago. It's worse than Sonnet. Opus is not much better. This cycle of new model running at full quantisation and then nerfed few days / weeks after premiere should be called out. Anthropic should also drop the adaptive reasoning scam. If I pay for Fable, I should get full, not nerfed model at honest pricing. Regulators should investigate them. OpenAI is no different. Astra has basically ", "context": "", "use_case": "", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}, {"id": 794936833, "item_id": 49683552, "url": "https://news.ycombinator.com/item?id=49683552", "by": "wdm0006", "date": "2026-09-13", "stance": "neutral", "quote": "in CC i use sonnet as main w/ opus advisor", "excerpt": "I use a lot of different harnesses, so in CC i use sonnet as main w/ opus advisor, in codex i use astra all the time, in obvious I usually use the GLM models. In general I've found that having a fast main model with a big smart advisor is a nice UX if I'm going to be on keyboard interacting with it, for a long-running agent that I'm not attending to I care much less about the main model speed and more about cost/qual", "context": "", "use_case": "main model", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794800033, "item_id": 49675002, "url": "https://news.ycombinator.com/item?id=49675002", "by": "jakevoytko", "date": "2026-09-12", "stance": "recommend", "quote": "For well-defined coding tasks, I'd default to either Luna or Sonnet", "excerpt": "My workhorse is Opus orchestrating Sonnet or Sol orchestrating Luna, depending on which ecosystem I'm using this week. I'm a backend engineer, so for tasks that either interact with the machine learning or client codebases, I have Fable (Medium) review across the product spec, tech spec, and all the codebases after the implementation is done (haven't tried this workflow with Astra yet, don't know if it's a good revie", "context": "backend engineer", "use_case": "well-defined coding tasks", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794782803, "item_id": 49673925, "url": "https://news.ycombinator.com/item?id=49673925", "by": "verisimilidude", "date": "2026-09-12", "stance": "neutral", "quote": "For planned implementation, I use Sonnet.", "excerpt": "It really depends. For high-level strategic conversations, I use Fable. For planning, I use Opus or Sol. Sol is generally preferred; it\u2019s faster, cheaper, and less verbose. But I still find Opus more capable on the most nuanced or complex tasks. For planned implementation, I use Sonnet. For one-shot unplanned implementation, I\u2019ll use whatever model seems best for the task. FWIW, I\u2019m increasingly turning to Grok here.", "context": "", "use_case": "planned implementation", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794778960, "item_id": 49673685, "url": "https://news.ycombinator.com/item?id=49673685", "by": "seabrookmx", "date": "2026-09-12", "stance": "recommend", "quote": "Sonnet. It makes my token budget go further and I prefer to have the LLM churn away on rote work while I do the thinking.", "excerpt": "Sonnet. It makes my token budget go further and I prefer to have the LLM churn away on rote work while I do the thinking. So while Opus and Fable are undoubtedly smarter, that doesn't materially affect _my_ workflow. I'm not as up to date on the other vendors' models, but when I last used Gemini my feelings were similar between Pro and Flash.", "context": "", "use_case": "rote coding work", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794777649, "item_id": 49673603, "url": "https://news.ycombinator.com/item?id=49673603", "by": "donatj", "date": "2026-09-12", "stance": "neutral", "quote": "My company pays for Claude so I use Sonnet in the office", "excerpt": "I feel like the odd man out ITT but Terra has been absolutely amazing for me and totally blows Sonnet out of the water. My company pays for Claude so I use Sonnet in the office but at home I use Terra and I find it far more likely to one shot some very decent code.", "context": "", "use_case": "office coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794776996, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "neutral", "quote": "Opus for planning, Sonnet for review", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "review", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794775280, "item_id": 49673455, "url": "https://news.ycombinator.com/item?id=49673455", "by": "codazoda", "date": "2026-09-12", "stance": "neutral", "quote": "I use Sonnit for my personal work and Opus for my professional work.", "excerpt": "I use Sonnit for my personal work and Opus for my professional work. For my personal stuff, I'm on a small $20 plan, so I need to use tokens conservatively. I was very rarely exceeding limits until I built a Dark Software Factory. It's not as efficient at token use. So, I use Sonnit over Opus here. At work I have a $100 plan that I rarely exceed so I use Opus. I have access to Fable too, and I did use it a lot while ", "context": "", "use_case": "personal work", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794771363, "item_id": 49673210, "url": "https://news.ycombinator.com/item?id=49673210", "by": "mariocesar", "date": "2026-09-12", "stance": "neutral", "quote": "most of the time it ends up choosing Opus or Sonnet.", "excerpt": "I have an 'ask' alias in my shell that just uses Haiku. I use it daily for pretty much everything For more long work, I now use Fable to create a PLAN.md. I tell it to make a plan that will be executed by other models, and most of the time it ends up choosing Opus or Sonnet. I didn't start doing this recently. Before that, I would just use the top model for everything. Splitting the work across different models depen", "context": "", "use_case": "executing plans", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794364469, "item_id": 49647779, "url": "https://news.ycombinator.com/item?id=49647779", "by": "tazo-lezhava", "date": "2026-09-10", "stance": "neutral", "quote": "we also used Claude Sonnet as an alternative judge", "excerpt": "Hi All, I'm cofounder and CEO of Quissly, author of the research piece published here. We tested 5 different search engines for ecommerce, and given we win across almost all benchmarks presented, you should read it with a grain of salt. We ran 1259 queries and 99,168 LLM judgements to get to the results presented in the report. Everything is reproducible from scratch, but we didn't use T=0 so you might not get identi", "context": "", "use_case": "LLM judge for benchmarks", "switched_from": "", "story": "Show HN: Ecommerce Search comparisson across 5 independent engines, all public"}, {"id": 794123634, "item_id": 49632727, "url": "https://news.ycombinator.com/item?id=49632727", "by": "surgical_fire", "date": "2026-09-09", "stance": "warn", "quote": "I honestly have more issues steering Sonnet properly.", "excerpt": "I used a lot V4 flash to implement plans built by other models, and it was honestly top notch. The thing was a workhorse, and I got none of the isuses you describe. I was mostly using DeepSeek on Pi, connecting to their API directly (not some third party provider). I honestly have more issues steering Sonnet properly.", "context": "", "use_case": "coding", "switched_from": "", "story": "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"}, {"id": 794024465, "item_id": 49626529, "url": "https://news.ycombinator.com/item?id=49626529", "by": "dsign", "date": "2026-09-09", "stance": "recommend", "quote": "I use Opus and Sonnet 5 all the time", "excerpt": "That was funny :-) I use Opus and Sonnet 5 all the time and I find their language grating. But honest, I prefer to put up with it and get the results than to put up with my own human limitations and not get the results.", "context": "", "use_case": "", "switched_from": "", "story": "Claude, change the \u201cAdd to Cart\u201d button to blue"}, {"id": 793162387, "item_id": 49572649, "url": "https://news.ycombinator.com/item?id=49572649", "by": "shubhamjain", "date": "2026-09-05", "stance": "compare", "quote": "I burned through my Claude Sonnet quota in just three days.", "excerpt": "> So this is just delegating certain work to dumber models? I certainly wouldn't use Gemini 2.5 Flash (!!?) for code writing as suggested. Why not, though? I started using OpenCode + GitHub Copilot, but I burned through my Claude Sonnet quota in just three days. I switched to GPT-5.4-mini, which uses far fewer tokens, and it\u2019s often just as good as Sonnet. I think optimizing token usage is a good exercise. We often a", "context": "", "use_case": "coding", "switched_from": "", "story": "Portal by Spotify cut my Claude Code token usage by 90%"}, {"id": 792552274, "item_id": 49534517, "url": "https://news.ycombinator.com/item?id=49534517", "by": "iLoveOncall", "date": "2026-09-02", "stance": "neutral", "quote": "Sonnet 4.5 at home (because it's free via Amazon Q)", "excerpt": "It absolutely is. What has improved isn't the models, it's the harnesses. Give GPT-3.5 a 1M context window and a modern harness, and you won't see any meaningful difference with Opus 5. It's a bit hard to try with such old models, but for example I use Opus 5 / Fable at work and Sonnet 4.5 at home (because it's free via Amazon Q), and there's absolutely 0 difference in performance. None. Obviously 4.5 is only a year ", "context": "", "use_case": "home coding", "switched_from": "", "story": "How accurate have Ed Zitron's AI skeptic predictions been?"}, {"id": 788762994, "item_id": 49297687, "url": "https://news.ycombinator.com/item?id=49297687", "by": "ilitirit", "date": "2026-08-14", "stance": "warn", "quote": "Sonnet isn't even worth considering in my world.", "excerpt": "I still haven't moved from Codex GPT5.5. Sonnet and Opus 5 have just been awful for my use cases. I recently caught Opus 5 hallucinating about code it just wrote. It's just not nearly as cost effective as GPT5.5, and it's too verbose, and it never \"has the full picture\". Sonnet isn't even worth considering in my world. Both recent models definitely feel nerfed.", "context": "", "use_case": "coding", "switched_from": "", "story": "Why does Opus 5 feel worse to work with?"}, {"id": 786132336, "item_id": 49133271, "url": "https://news.ycombinator.com/item?id=49133271", "by": "aetherspawn", "date": "2026-08-01", "stance": "recommend", "quote": "try Sonnet 5, it has no guardrails and it can run continuously", "excerpt": "Yeah try Sonnet 5, it has no guardrails and it can run continuously. Hook it up to IDA, or I use Ghidra, with MCP and it can autonomously search for whatever you tell it to using a text prompt. It\u2019s way faster than doing it by hand. Only issue is Sonnet is kind of a silly model and whilst it\u2019s good at searching for stuff, it lacks a little bit of common sense compared to Opus or Fable, so you\u2019ll have to drive it. You", "context": "reverse engineer", "use_case": "autonomous reverse engineering", "switched_from": "", "story": "Twenty-five years ago it was cryptography, today it's model weights"}, {"id": 785336720, "item_id": 49083545, "url": "https://news.ycombinator.com/item?id=49083545", "by": "oggreen", "date": "2026-07-28", "stance": "recommend", "quote": "I use Sonnet 80% of the time when I'm on claude.ai", "excerpt": "I use Sonnet 80% of the time when I'm on claude.ai and on Claude Code my main agent is Opus and typically my sub-agents are Sonnet. I use this setup mainly because I genuinely don't know if anything I'm doing is complex enough to need Fable and I don't want to run up my usage too much. It's basically like trying to kill a gnat with a sledgehammer. Hell, at work Haiku almost always works just as well as Sonnet does an", "context": "", "use_case": "everyday AI tasks and sub-agents", "switched_from": "", "story": "Why I prefer Opus 5 to Fable 5"}, {"id": 784630992, "item_id": 49039437, "url": "https://news.ycombinator.com/item?id=49039437", "by": "plqbfbv", "date": "2026-07-24", "stance": "recommend", "quote": "I daily drive Sonnet 5/medium because it gets most things right most of the time at first try", "excerpt": "I daily drive Sonnet 5/medium because it gets most things right most of the time at first try, while costing a lot less than Fable. Opus can give better results on architectural/concept tasks and I use it sparingly, but it still costs more than Sonnet 5. Opus 5 seems to achieve results very close to Fable 5 while costing less (keeps Opus 4.8 pricing IIUC), but still more than Sonnet 5 then.", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Claude Opus 5"}, {"id": 780833731, "item_id": 48802108, "url": "https://news.ycombinator.com/item?id=48802108", "by": "schnitzelstoat", "date": "2026-07-06", "stance": "recommend", "quote": "I just use Opus for planning and Sonnet for implementation and it's pretty cheap", "excerpt": "My company has a Claude Code and Codex one and I use Claude Code because I am more familiar with it. That said, I just use Opus for planning and Sonnet for implementation and it's pretty cheap. Codex seems decent too so I should try it out some more. But you can get an awful lot done even with just like $200 a month at API pricing if you are careful not to waste a powerful model on an easy task, or carry around a blo", "context": "", "use_case": "implementation", "switched_from": "", "story": "When AI Costs More Than the Engineer"}, {"id": 780031344, "item_id": 48751959, "url": "https://news.ycombinator.com/item?id=48751959", "by": "vlan121", "date": "2026-07-01", "stance": "warn", "quote": "Performance is worse than Opus 4.8", "excerpt": "Changelog: https://github.com/anthropics/claude-code/releases Performance is worse than Opus 4.8: https://www.anthropic.com/news/claude-sonnet-5", "context": "", "use_case": "", "switched_from": "", "story": "Claudes newest update is putting a worse model to default"}, {"id": 779895376, "item_id": 48743461, "url": "https://news.ycombinator.com/item?id=48743461", "by": "seviu", "date": "2026-07-01", "stance": "warn", "quote": "new Sonet is a dumbed down expensive model, which already falls behind GLM 5.2 and Kimi 2.7.", "excerpt": "This. I have been using anthropic and codex subs, on max. All this changed in June. We are clearly entering an era where we cannot rely on American models. As a solo developer I value reliability over performance. I cannot pay hundred of $, plus a lot of my private time figuring out how to properly use this technology, for it to be taken away within hours. On top of that, the intelligence is being dialed down. Sonet ", "context": "solo developer", "use_case": "coding", "switched_from": "", "story": "Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5"}, {"id": 779829664, "item_id": 48739354, "url": "https://news.ycombinator.com/item?id=48739354", "by": "butterisgood", "date": "2026-06-30", "stance": "recommend", "quote": "I would use sonnet 5 for coding \u2026 seems alright!", "excerpt": "I used sonnet five today to evaluate work I\u2019m doing on an experimental programming language with an interesting concurrency model. I asked it to try to figure out why one of the examples wasn\u2019t working. It read the implementation of the compiler and the runtime, found the bug, fixed it, fixed the example and the only thing I had to do manually is suggest a less silly name for a particular function. I would use sonnet", "context": "working on an experimental programming language", "use_case": "debugging and fixing code", "switched_from": "", "story": "Claude Sonnet 5 \u2013 benchmark results"}]}