OpenAI GPT

What hackers pick instead

• Claude OpusRecommended as a top coding model that fixes bugs and ships features with fewer mistakes than earlier LLMs, though critics cite weak architecture choices, usage limits and confident errors.3331recommend
• 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 3312 comments. Each links to the original.

1. I could probably accomplish most of the same tasks with GPT-5.0, but it would take a lot more involvement from me, more troubleshooting, and significantly more time.

   Mixed · Jul 2026 · in “Ask HN: What was the last task where only a frontier model could do it?”

2. GPT can be very creative when discussing a high-level design. Once it starts writing code snippets it will offer to take things in a bunch of different directions.

   Mixed · Jun 2026 · in “Local Qwen isn't a worse Opus, it's a different tool”

3. I used GPT-4 as a second opinion on my medical tests and doctor's advice, and it suggested an alternate diagnosis and treatment plan that turned out to be correct.

   Recommends · Nov 2025 · in “ChatGPT terms disallow its use in providing legal and medical advice to others”

4. for more mechanical refactoring work (like splitting a big source code file into multiple smaller ones), GPT 5.5 runs way faster than any of the Claude models

   Recommends · Jul 2026 · in “Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers”

5. Most variants of GPT-5.5 are less chatty and token-intensive than Opus 4.8/4.7, so despite the output token price being higher, it generates fewer tokens

   Recommends · May 2026 · in “Anthropic raises $65B in Series H funding at $965B post-money valuation”

6. Anecdotally, GPT 5.5 seems decent, but it's rumored to be a 10T parameter model, isn't noticeably better than 5.4 or 5.3, is insanely expensive to use

   Mixed · May 2026 · in “Let's Talk about LLMs”

7. I've found GPT/Codex models consistently stronger in engineering tasks (such as debugging complex, cross-systems issues, concurrency problems, etc).

   Recommends · Apr 2026 · in “ChatGPT Pro now starts at $100/month”

8. answer all my tax questions correctly. Those thousands of dollars in time and money I had spent has been replaced by a single $20 subscription.

   Recommends · Aug 2026 · in “Denmark Requires Oral Defenses for Students' Written Work to Counter AI Cheating”

9. it does seem like a step change in token efficiency, though based on the earlier artificial analysis reporting it's also quite the cost lottery

   Mixed · May 2026 · in “GPT-5.5 Price Increase: What It Costs”

10. GPT 5.5 which quite literally worked through the night day (with the /goal feature), and actually had something valuable and useful in the end

    Recommends · Jun 2026 · in “GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2”

11. which in my opinion are unlikely to have been used for anything serious, as they're simply several times more expensive than any human effort

    Mixed · May 2026 · in “Microsoft Drops Claude Code After Budget Overrun”

12. I do prefer the overall results with GPT 5.4, which seems to catch more bugs in reviews that Gemini misses and produce cleaner code overall.

    Recommends · Apr 2026 · in “Our eighth generation TPUs: two chips for the agentic era”

13. I use gpt 5.5 high with planning every time and plan various smaller features/changes in parallel, then approve them one after another.

    Recommends · Jul 2026 · in “GLM 5.2 and the coming AI margin collapse”

14. end up with a report indistinguishable in accuracy and bibliographic quality from what a good human might produce in a couple of weeks

    Recommends · Jan 2026 · in “Bending Spoons laid off almost everybody at Vimeo yesterday”

15. GPT 5.2 Pro is decently ahead of Claude Opus 4.5 in this category when it gets to the tricky stuff, both in presentation and accuracy.

    Recommends · Feb 2026 · in “Advancing finance with Claude Opus 4.6”

16. it can walk away for 45 minutes, produce CoT with a length of Empire State Building and give me fairly good and well written response

    Recommends · Jan 2026 · in “The rapid rise and slow decline of Sam Altman”

17. GPT 5.5 is a good example of a model that's generally better at solving problems than Opus 4.8, but the code it generates is worse

    Mixed · Jul 2026 · in “GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday”

18. You can give it a picture of electrical wiring, plumbing, framing and it will tell you if it's up to code with very good accuracy.

    Recommends · Aug 2026 · in “Starbase, LA”

19. Since when has a junior level dev managed to debug and deploy say a cloudformation stack and follow up with notes under 3 minutes?

    Recommends · Apr 2026 · in “OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API”

20. Still waiting for them to fix the real issue: the model's pathological need to apologize for everything and hedge every statement

    Mixed · Nov 2025 · in “GPT-5.1: A smarter, more conversational ChatGPT”

21. AI agent understands nothing of the UI. If you tell it "Make buttons evenly spaced", sure it will space them evenly, but without care for the context they are placed in.

    Criticizes · Mar 2026 · in “Show HN: ProofShot – Give AI coding agents eyes to verify the UI they build”

22. GPT-5.3+ are some of the smartest models out there and could be a pleasure to work with, if they weren't lazy bastards to the point of being completely infuriating.

    Criticizes · Apr 2026 · in “OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API”

23. Receiving a half-baked, extremely verbose recap of thinking on benign details with Opus 4.8 or GPT 5.5 feels like an extraordinary loss of quality of experience

    Criticizes · Jul 2026 · in “GPT-5.6”

24. hallucinated the existence of two CLI utilities, and when corrected, then hallucinated the existence of non-existent, but plausible, features/options

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

25. It's a cash grab. More conversational AI means more folks running out of free or lower paid tier tokens faster, leading to more upsell opportunities.

    Criticizes · Nov 2025 · in “GPT-5.1: A smarter, more conversational ChatGPT”

26. 5 made nonsense changes (based on the apparently incorrect guess that the missing 'index_value' column was supposed to hold the value of the index)

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

27. GPT's output is awful and it gets even more awful when you try to work out a solution "together" because it shits out 10 paragraphs with 20 options

    Criticizes · Apr 2026 · in “Changes to GitHub Copilot Individual Plans”

28. It was going in loops hallucinating features of GCP, looking things up in strange ways, running terraform apply after being explicitly told not to

    Criticizes · Jun 2026 · in “/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds”

29. 5.5 is overcomplicating it. Where the solution is e.g. changing some oidc auth url, it goes around and verifies and check and builds this and that

    Criticizes · May 2026 · in “GPT-5.5 Price Increase: What It Costs”

30. GPT-5 models are much more fixated on solving exactly the problem given and not as good at taking a step back and thinking about the big picture

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

31. 4 failed to follow the prompts in 4/10 cases and made nonsense changes in the other 6

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

32. 4.1 made nonsense changes

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

33. Amazing capabilities. The entire "low code drag n drop" market like YoYoGames Game Maker and RPG Maker should be ready to pack it in soon if this keeps improving

    Recommends · Mar 2026 · in “GPT-5.4 Thinking and GPT-5.4 Pro”

34. I'm absolutely ok with a legitimate lab scientist conducting biochemical research getting suggestions about substances that are generally considered dangerous

    Recommends · Apr 2026 · in “GPT‑Rosalind for life sciences research”

35. The next major increment is going to happen when marketing department is confident they can sell it as a major improvement without everyone laughing at them.

    Mixed · Apr 2026 · in “Introducing GPT-5.5”

36. Reinforcement learning with verifiable rewards training is actually the secret sauce that is leading Claude and GPT to automating software engineering tasks.

    Recommends · May 2026 · in “The Sigmoids Won't Save You”

37. They tried a new technology, modeled (literally) on us as reasoners, that is only just being able to reason at their level and it did what they couldn’t.

    Recommends · Feb 2026 · in “GPT-5.2 derives a new result in theoretical physics”

38. My confidence in frontier model's ability to generate "good enough, probably more than good enough" from this level of meal description is quite high.

    Recommends · Aug 2026 · in “Software for One”

39. For chatting and getting informations, and be corrected on things you're wrong without being reprimended by your own tool, GPT 5.5/5.6 is way better.

    Recommends · Jul 2026 · in “I used to love Claude, but the latest models are slowly ruining it”

40. I do agree that GPT5 tends to have a better agentic dispatch style for math questions but I've found it has really struggled with data model design.

    Mixed · Dec 2025 · in “OpenAI declares 'code red' as Google catches up in AI race”