Fable

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
• 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
• 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 2219 comments. Each links to the original.

1. I have to agree on fable being in another league. I've given it my most challenging problems and almost always comes back with a functional, solution 2-5 prompts away from a finished pr.

   Recommends · Jul 2026 · in “The real prices of frontier models. Tokens * Price, right?”

2. Fable is the first one I've encountered that is capable of serious open ended 3D programming in ways that suggest it has some grasp of the spatial aspects of the problem

   Mixed · Jul 2026 · in “GPT-5.6 used a prompt to close a 30-year gap in convex optimization”

3. I'm really soley dependent of Fable to the point that I don't use other models, and I've already sort of hit a point where I'm running into usage limits every week.

   Mixed · Aug 2026 · in “The Harness Is the Thing”

4. I recently launched a project for a client that integrated many many systems, has considerable traffic with low latency requirements and everything just.. works.

   Recommends · Sep 2026 · in “Fuck it, make it anyway”

5. Fable is able to handle that long goal, with incremental steps along the way, handle the verification and course correct when it finds a problem.

   Mixed · Aug 2026 · in “Anthropic's best AI model struggles to attract users as cheaper tools thrive”

6. It is as if Fable skipped any basic writing class, but went straight to poetry, advertising-copy and CEO-speak classes and somehow combined them.

   Mixed · Sep 2026 · in “"Please Remove All Mannered Prose" and Other LLM Incantations”

7. It works much better on regular software development e.g. for complex refactoring where cheaper models would produce a lot of garbage results.

   Recommends · Aug 2026 · in “Anthropic's best AI model struggles to attract users as cheaper tools thrive”

8. Fable was doing really well for me too, and I had scoped out a nice development plan that was going to come in on-time under token budget

   Mixed · Jul 2026 · in “Ask HN: Did Fable disappear from your Claude usage and requires credits now?”

9. If the new Fable only changed the writing style to just sound like a human, same performance for everything else, I'd be pretty happy.

   Mixed · Sep 2026 · in “Claude Opus 5.5”

10. Fable is seriously good enough now to, in a 20k line project, take "replace Mongoengine with raw PyMongo" and not screw anything up.

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

11. Fable is very steerable. For me it makes the "simplest thing that works" and - once I tuned it - very understandable explanations.

    Recommends · Aug 2026 · in “GLM-5.3 (open-weight) beat Anthropic/OpenAI models – for 1/5 the cost”

12. Like laughably over-complicated. With a bit more back and forth I was able to cut hundreds of lines of code down to less than 100.

    Mixed · Sep 2026 · in “Coding is not solved”

13. I only realised late that I had an algorithm problem that existing models were struggling with, and Fable had made progress with.

    Recommends · Jul 2026

14. I find Fable completely unbeatable for anything code-related. It's the only frontier model that seems to come with sane defaults.

    Recommends · Aug 2026 · in “Gemini 3.7 Flash”

15. This seems to be what Fable is solving since it is capable of doing much larger chunks of work without needing input constantly.

    Recommends · Jul 2026 · in “Ask HN: Is anyone experimenting with different ways of using LLMs for coding?”

16. I'd definitely pick the "understanding" of Fable over a junior engineer's "understanding" any day, for purely pragmatic reasons.

    Recommends · Jul 2026 · in “AI is 'not smart' so what's next in artificial intelligence?”

17. Fable took 5 minutes and found the server grade Nic card's driver I use has a known rare problem where in certain configuration

    Recommends · Oct 2026 · in “JetBrains reports revenue growth, net financial loss for 2025”

18. What makes Fable so much better than Opus besides being a better coder is that it's personality and judgment are far superior.

    Recommends · Jul 2026 · in “Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA”

19. Fable reported to me like a colleague (researcher). It genuinely seemed to pick up on nuance that the other models just don't

    Recommends · Jun 2026 · in “Will It Mythos?”

20. one engineer can manage a team of 20 fable subscriptions more effectively than a team of 3 of last year's model subscriptions

    Recommends · Aug 2026 · in “Fable and the end of the free lunch”

21. I've managed to fix several long-standing issues by just giving Fable access to my configuration and telling it my intent.

    Recommends · Sep 2026 · in “One resignation turned the embers of AI fear into a wildfire”

22. Re-wrote massive parts of my codebase and caught a ton of bugs and logic issues that had silently slipped through before.

    Recommends · Jun 2026 · in “Claude Sonnet 5”

23. the code becomes over-complex, over-engineered and more often than not, it will take a specific point and iterate over it

    Mixed · Jul 2026 · in “Terrence Tao's ChatGPT Conversation about the Jacobian Conjecture Counterexample”

24. Fable was absolutely maximalist. We tested it on a fairly innocuous looking prompt and it ended up working for an hour and costing roughly 1000 dollars in tokens.

    Criticizes · Jun 2026 · in “Will It Mythos?”

25. The triple whammy of (a) two layers of annoying timed usage windows, (b) constantly changing model availability windows, and (c) random unpredictable usage resets

    Criticizes · Jul 2026 · in “Fable extended until 19 July”

26. Fable smacked me for asking it to design a secure app without obvious security flaws and to double check it wasn't using libraries with known security problems.

    Criticizes · Jul 2026 · in “Microsoft – Open Weights and American AI Leadership”

27. A lot of incidents where it would creat some giant complex set of abstractions to accomplish something that I could find ways to do much more elegantly

    Criticizes · Jun 2026 · in “When I reject AI code even if it works”

28. That triggered its safety guards, which converted the thing to opus, leaving opus to run the rest of the night, wasting my precious time with Fable.

    Criticizes · Jul 2026 · in “Agentic coding notes from Galapogos Island”

29. the thing with fable is so bad; for some project related questions, the model switches to opus to ensure safety with no further explanation

    Criticizes · Sep 2026 · in “Nvidia wants to put a watchdog chip next to every AI agent”

30. There are whole classes of things I can’t thought exercise or really learn about because the “safeguards” keep tripping me down to haiku.

    Criticizes · Aug 2026 · in “Fable and the end of the free lunch”

31. Very expensive, not sure how it fits in with many companies seemingly trying to get employees using models at about Sonnet tier pricing.

    Criticizes · Jul 2026 · in “Ask HN: Fable Thread (July 12th Edition)”

32. It overengineered, obscured and picked awkward constructs all the time over plain, simple, perfectly clean and performant code patterns.

    Criticizes · Aug 2026 · in “Fable and the end of the free lunch”

33. produces a passable 3Blue1Brown-style explainer video of the algorithms it just implemented that sounds like it's narrated by a character from Dora the Explorer

    Mixed · Jun 2026 · in “Waveloop: What Fable Left Me”

34. it might not be because it lacks boundaries, but rather because you haven't put it through a sufficiently real, complex, and verifiable production environment

    Recommends · Jul 2026 · in “What Can't Fable Do?”

35. The models are great at the monotony, like constructing a Gröbner-basis, etc. But they're all still absolutely awful at coming up with new ideas

    Mixed · Sep 2026 · in “Caltech Mathathon – first hackathon ever devoted to research level mathematics”

36. If benchmarks and early tester impressions are accurate, you also get access to Fable level capability at greater speed and lower cost

    Mixed · Jul 2026 · in “GPT-5.6”

37. Fable MAX is the thing that gets me much closer to "just send emails" but even then it doesn't look in my specs directory for the spec

    Mixed · Jul 2026 · in “AI Mania Is Eviscerating Global Decision-Making”

38. I'm using both extensively at the moment and I've not yet found that either is demonstrably better at specific tasks than the other.

    Recommends · Sep 2026 · in “Altman tells staff OpenAI is open to slowing AI development”

39. The best models can hold increasingly nuanced discussions on new features and ideas, and write a lot better code than they used to.

    Recommends · Jul 2026 · in “The Short Leash AI Coding Method for Beating Fable”

40. Left me that code and a massive code review that unfortunately didn't contain any of the I/O and memory safety hardening I wanted.

    Mixed · Jun 2026 · in “Waveloop: What Fable Left Me”