# Fable 823 Hacker News commenters recommended Fable and 745 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months; owners who said how long report a median of 0.04 years (14 owners). **Verdict:** Recommended 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. ## Why people recommend it - Excellent at complex coding work (6 comments): "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." ([source](https://news.ycombinator.com/item?id=48898309)) "I recently launched a project for a client that integrated many many systems, has considerable traffic with low latency requirements and everything just.. works." ([source](https://news.ycombinator.com/item?id=49675524)) "It works much better on regular software development e.g. for complex refactoring where cheaper models would produce a lot of garbage results." ([source](https://news.ycombinator.com/item?id=49412085)) - Handles long tasks autonomously (4 comments): "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." ([source](https://news.ycombinator.com/item?id=49415729)) "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" ([source](https://news.ycombinator.com/item?id=48950846)) "This seems to be what Fable is solving since it is capable of doing much larger chunks of work without needing input constantly." ([source](https://news.ycombinator.com/item?id=48779694)) - Solves problems other models can't (4 comments): "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" ([source](https://news.ycombinator.com/item?id=48959431)) "I only realised late that I had an algorithm problem that existing models were struggling with, and Fable had made progress with." ([source](https://news.ycombinator.com/item?id=48742745)) "Fable took 5 minutes and found the server grade Nic card's driver I use has a known rare problem where in certain configuration" ([source](https://news.ycombinator.com/item?id=49993007)) - Good judgment and nuance (4 comments): "Fable is very steerable. For me it makes the "simplest thing that works" and - once I tuned it - very understandable explanations." ([source](https://news.ycombinator.com/item?id=49413664)) "I'd definitely pick the "understanding" of Fable over a junior engineer's "understanding" any day, for purely pragmatic reasons." ([source](https://news.ycombinator.com/item?id=48780026)) "What makes Fable so much better than Opus besides being a better coder is that it's personality and judgment are far superior." ([source](https://news.ycombinator.com/item?id=49003725)) ## What people warn about - Over-engineered, overly complex code (4 comments): "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." ([source](https://news.ycombinator.com/item?id=49882857)) "the code becomes over-complex, over-engineered and more often than not, it will take a specific point and iterate over it" ([source](https://news.ycombinator.com/item?id=49019847)) "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" ([source](https://news.ycombinator.com/item?id=48615105)) - Safety guards downgrade to other models (4 comments): "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." ([source](https://news.ycombinator.com/item?id=49049570)) "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." ([source](https://news.ycombinator.com/item?id=48786544)) "the thing with fable is so bad; for some project related questions, the model switches to opus to ensure safety with no further explanation" ([source](https://news.ycombinator.com/item?id=49891313)) - Expensive with restrictive usage limits (4 comments): "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." ([source](https://news.ycombinator.com/item?id=49455338)) "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." ([source](https://news.ycombinator.com/item?id=48657456)) "The triple whammy of (a) two layers of annoying timed usage windows, (b) constantly changing model availability windows, and (c) random unpredictable usage resets" ([source](https://news.ycombinator.com/item?id=48882819)) - Grating, ad-copy writing style (2 comments): "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." ([source](https://news.ycombinator.com/item?id=49621043)) "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." ([source](https://news.ycombinator.com/item?id=49805080)) ## Alternatives hackers recommend - [Claude Opus](https://hackerapproved.com/p/claude-opus.md): 3331 recommend - [OpenAI GPT](https://hackerapproved.com/p/gpt-5-5.md): 1205 recommend - [Claude Sonnet](https://hackerapproved.com/p/claude-sonnet.md): 854 recommend - [DeepSeek V4 Flash](https://hackerapproved.com/p/deepseek-v4-flash.md): 828 recommend - [Claude Fable 5](https://hackerapproved.com/p/fable-5.md): 774 recommend ## Cite as Hacker Approved, "Fable", https://hackerapproved.com/p/fable/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).