Claude Opus

What hackers pick instead

• OpenAI GPTRecommended for strong coding, debugging and research help with good reasoning and token efficiency, though critics cite hallucinations, overcomplication, verbose output and high cost.1205recommend
• Claude SonnetA capable coding model that has improved noticeably with each version and is faster and cheaper than Opus, though it needs careful supervision and usage limits bite.854recommend
• DeepSeek V4 FlashA very cheap, fast model that people find close to frontier quality for coding and everyday tasks; critics say it errs more, loops, and needs steering.828recommend
• FableRecommended as a top coding model for hard, long-running tasks and large refactors, though critics cite over-engineered code, costly usage limits and safety guards that switch models mid-task.823recommend
• Claude Fable 5Recommended for long-horizon agentic work and hard reasoning, debugging and research problems where it beats Opus, though overbroad safety filters often block legitimate security and biology tasks.774recommend

Every quote

The 40 most detailed of 10697 comments. Each links to the original.

1. For complex non-coding work (research, in-depth analysis, assembly of complex info-dense documents) I'd rather do it by hand than switch from Opus 4.7 to anything I could even theoretically run locally.

   Mixed · Jun 2026 · in “32GB of DDR5 now costs $375 – AI shortage continues to squeeze PC building”

2. It's really good at fixing bugs in an established architecture or adding a similar feature, but it's absolutely mid tier at putting together a simple effective architecture

   Mixed · Aug 2026 · in “Databricks drove down AI coding spend 70%”

3. When Opus 4.5 entered the picture, there was a noticeable improvement in the way the LLM (for me), interacted with the code base, and the issues that it was able to find.

   Recommends · Feb 2026 · in “AI is going to kill app subscriptions”

4. Even though I find Opus-es to be more well-rounded (and more useful) for certain tasks, I instinctively reach for ChatGPT / codex to avoid burning up my usage limits

   Mixed · Feb 2026 · in “Claude Opus 4.6”

5. I think Opus 4.5 & 4.6 are an impressive step up in capabilities but I'm really skeptical that this model is replacing the output of 9/10 skilled front end engineers

   Mixed · Feb 2026 · in “The AI Vampire”

6. Opus doesn't appear to refuse on simple keywords, but it does seem like Fable's reasoning introduces enough nefarious-sounding context that Opus will then refuse

   Mixed · Aug 2026 · in “GLM-5.3: Frontier Coding with Emergent Cyber Capabilities”

7. I don't recall i last few weeks where Opus 5.5 in CC made an obvious lie, made an unreasonable assumption, or made a mistake that smart human couldn't make.

   Recommends · Oct 2026 · in “The gap in shared understanding of LLM capability is widening”

8. if you tell a frontier LLM, like Opus 4.6, "Turn this paper into an interactive web page highlighting the most important aspects" it does a really good job

   Recommends · Feb 2026 · in “Show HN: Now I Get It – Translate scientific papers into interactive webpages”

9. Claude web finds a number of small discrepancies in the sources, which I manually crosschecked and seem consistent with a human mixng things up slightly.

   Recommends · May 2026 · in “Check Your Fucking Sources, People”

10. Claude Code and Opus really took off when they improved the harnessing enough that it would self-correct many of its mistakes without needing user input

    Recommends · Jun 2026 · in “GLM 5.2 vs. Opus”

11. as of opus 4.6 they can now one shot full features in a complex js/go data streaming & analysis tool but implode in low latency voice synthesis systems

    Mixed · Feb 2026 · in “The consequences of task switching in supervisory programming”

12. I've been using Claude Opus exclusively for while and it doesn't tend to make those mistakes nearly as often as I used to see with lower-powered LLMs.

    Recommends · Apr 2026 · in “Deezer says 44% of songs uploaded to its platform daily are AI-generated”

13. Opus5.5 and other models are very limited by their own safety, I have digital twins of our infra and I want LLMs to actually write full exploits on it

    Mixed · Nov 2026 · in “Anthropic blocks users for anything touching training larger models”

14. It both confidently makes shit up, claims it is mathematically justified and when the resulting simulation explodes says "I apologise; I lied above"

    Mixed · Jun 2026 · in “Claude Fable 5”

15. The frustrations with previous models going off the rails, getting stuck in loops, hacky solutions or bad code are almost completely gone with Opus.

    Recommends · Jan 2026 · in “AI Coding Assistants Are Getting Worse”

16. I've found models (codex-5.1-max, opus 4.5) to be absolutely useless writing shaders or ML training code, but really good at basic web development.

    Mixed · Dec 2025 · in “GPT-5.2”

17. I don't question that (coding) LLMs have started to be useful in my day-to-day work around the time Opus 4.5 was released. I'm a paying customer.

    Recommends · Feb 2026 · in “I want to wash my car. The car wash is 50 meters away. Should I walk or drive?”

18. Claude Opus 5 is insane. Still not able to do big complex projects well start to finish but it can, with guidance, implement large parts of them.

    Recommends · Aug 2026 · in “Is it all just vapourware?”

19. Opus and the like is amazing at Python, honestly sometimes better than me but it does do some really stupid architectural decisions occasionally.

    Mixed · Mar 2026 · in “1M context is now generally available for Opus 4.6 and Sonnet 4.6”

20. I have been trying to work on debugging tools using Opus 4.8. As it turns out working with low-level techniques that inspects and alters behavior of other processes is bordering close enough to cybersecurity research that it often hits the guardrails.

    Criticizes · Jun 2026 · in “Making Claude a Chemist”

21. Careless use, I guess. I was fixing a bunch of mocks in some once-great but now poorly maintained code, and I wasn't really feeling it so I just fed everything to Claude. Opus, unfortunately. I could easily have downgraded a bit.

    Criticizes · Jan 2026 · in “Opus 4.5 is going to change everything”

22. They reduced the cache TTL to one hour so if you leave your prompt sitting idle for an hour at 700,000 tokens the next time you hit enter send it it will be completely uncached and eat a ton of tokens.

    Criticizes · Apr 2026 · in “Claude Opus 4.7”

23. it quickly fills much of the claude opus context window with relevant documentation alone, and even then repeatedly outputs things directly counter to the documentation it just ingested

    Criticizes · Feb 2026 · in “I Miss Thinking Hard”

24. I've recently seen Opus, after struggling for a bit, implement an API by having it return JSON that includes instructions for a human to manually accomplish the task I gave it.

    Criticizes · Jan 2026 · in “Don't fall into the anti-AI hype”

25. if the text you pass it looks roughly like it could have been written by some famous internet personality, it will very confidently say that it was written by that personality

    Criticizes · May 2026 · in “Opus 4.7 knows the real Kelsey”

26. tell me the other (or another instance) did a great job with test coverage and depth, only to find tests within that just asserted the test harness had been set up

    Criticizes · Mar 2026 · in “You hired the AI to write the tests. Of course they pass”

27. A company that has not rejected agreements with a "Department of War" and sanctions reasoning models to enable mass citizen surveillance and autonomous weapons deployment with no human intervention is not really the kind of company I want to give my money too.

    Recommends · Apr 2026 · in “Anthropic no longer allowing Claude Code subscriptions to be used with OpenClaw”

28. Their bleeding-edge research culture and strong focus on software engineering above everything else are two competitive advantages that no other frontier labs are even trying to do the hard work in these areas required to displace.

    Mixed · Oct 2026 · in “The obscure trust looming over Anthropic's IPO”

29. From my experience Opus is only good at writing Rust. But it's great at something like TS because the amount of code it has been trained on is probably orders of magnitude bigger for the latter language.

    Mixed · Jan 2026 · in “Building a Rust-Style Static Analyzer for C++ with AI”

30. If I showed the kid version of myself what I can do with Opus or Nano Banana or Seedance, let alone broadband and smartphones, I think I'd feel we were living in the Star Trek future.

    Recommends · Apr 2026 · in “The next phase of the Microsoft OpenAI partnership – OpenAI”

31. it may be exceedingly annoying to chat with, I sort of wonder whether this metaphorical-reasoning behavior has been selected for precisely because it leads to better coding outcomes

    Mixed · Aug 2026 · in “Why does Opus 5 feel worse to work with?”

32. many of the scenes have obvious markers of slop (impossible intersecting geometry, bridges to nowhere, and so on), the scenes largely do work to convey the intended concept/emotion

    Mixed · Oct 2026 · in “I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities”

33. as long as Anthropic maintains the perception that Opus is even slightly better than the best OSS models, they'll still be the preferred tool for professional developers

    Recommends · Apr 2026 · in “Claude Opus 4.7”

34. giving opus 4.7 two sentences about building a cli doing Finnish to English translation and looking for a space efficient solution leads to an answer pointing to fst

    Recommends · May 2026 · in “Replacing a 3 GB SQLite db with a 10 MB FST (finite state transducer) binary”

35. Sometimes models do some things better but become so annoying and obtuse in their other doings that it's just not worth it (like Opus with the insane code comments

    Mixed · Sep 2026 · in “GPT-6 Sol and Luna”

36. Sometimes they can one-shot many related changes in a single prompt but the common reality is what you experienced: it works sometimes but the code is suboptimal.

    Mixed · Jan 2026 · in “Opus 4.5 is going to change everything”

37. Diffing and only updating the parts of the TUI which have changed does make sense if you consider the alternative is to rewrite the entire screen every "frame"

    Mixed · Feb 2026 · in “Claude Opus 4.6”

38. enforcing this via system prompt for such a powerful model like Opus 4.8 doesn't feel like the Anthropic themselves treat it as something with 'intelligence'

    Mixed · Aug 2026 · in “Claude: System Prompts”

39. although Opus 5 shows improvements in its ability to identify software vulnerabilities, it is substantially behind Mythos 5 in its ability to exploit them.

    Mixed · Jul 2026 · in “Claude Opus 5”

40. Once you work somewhere that gives you unlimited opus 4.6 and learn how to use it properly, your perspective of what you should be doing day to day shifts.

    Recommends · Apr 2026 · in “SpaceX and Cursor partnership. Right to acquire Cursor later this year”