Hacker News Reader

I like super powers because I can be more in the loop editing and understanding the plan. Letting fable loose is genuinely impressive, and probably perfect for vibe coding, but I can’t be that far away from the plan and steps for code that matters.

As for being great for vibe coding, it’s cool but I can’t justify that kind of cost for throwaway code. At this point I’ve had good experiences using fable to review code, but I’m totally content with opus for all of my workflows still. If fable was the same price I’d switch (for projects not involving biology, at least), but I’d still use something like super powers to stay in the loop.

This is an interesting comment because it makes me want to ask the question, what is the use for fable then? For me, GPT 5.4 is enough when using recursive-mode. I do appreciate GPT 5.5 Pro for some larger research, architecture, planning tasks though. I think that's what Fable is for. A very small % of total work.

> what is the use for fable then?

Cybersecurity hardening. The one thing they don't allow the model to do.

That’s Mythos. Fable isn’t specifically for that I don’t think, just an enhanced ability and persistence of Opus.

Fable is itself a "Mythos class" model. It can do everything Mythos can do. Anthropic's classifier just doesn't allow it to do it.

Definitely not just a classifier layered on top, although there is one of those as well. Pretty sure it's different post-training / finetune run and the model weights are different between them. Which is bound to have effects on the model output even in general use, although I'd imagine they have pretty stringent evals to make sure it doesn't regress too much in things they don't want to restrict.

Fable is consumer-branded Mythos.

> A very small % of total work.

That seems valid in today's world. Right now it's expensive, slow, and accurate. I imagine in the fairly near future it will be cheap, slow, and accurate, and that'll be a great opportunity to let it run on anything time-insensitive.

Re current use-cases: in addition to planning, there's also some tasks which Opus just can't complete but Fable can. Multiple times I've spent hours in combination w/ Opus trying to debug some particularly nasty nondeterministic issue, only to have Fable nail it in 20mins while I walk the dog.

>planning tasks though. I think that's what Fable is for.

this is how i've been using it, and where i've found it really excels over anything else i've tried. get fable to write a plan, and get something cheaper to follow the plan. the code fable writes isn't significantly better than the code opus writes, as long as they're both following the same plan. but a plan written by fable is much better.

What is the use of a genius who does great work but doesn’t document their results, only produces them? How much do companies enjoy having a structural dependency on someone like that?

I think it depends on your workflow. I've had a great experience with the trial. I work in research, and have set up something similar to Kaparthy's auto research. I, with Fable, have managed to get an image generation model down from 80M parameters to 10M and keep the quality of the generated images on par (similar FID). And, importantly, every change was modular, explained by Fable, reviewed by myself, and understood and documented. If not understood, I read relevant docs until I did it didn't accept it as part of the plan. So it ended up being a simple composition of existing ideas which I had previously encountered, but stacked much more rapidly than I could have.

The structure of the code is easily readable as I enforce concenventions followed by good libraries. And I can easily plug in new datasets. It's pretty good frankly.

(Not a Claude user) What is "superpowers"?

https://github.com/obra/superpowers

Some people just need to complicate things as a state of their natural being. What a tremendous waste of time.

That's funny, cause I'd argue superpowers barely does anything, and you need a much more complex setup to gain value.

I find it very useful. What do you use that’s better?

I don't want to turn this into an, oh look at mine.

It's just always been very behind the curve. I don't think you should use anyone's honestly. You should create your own shell base, and point to skills you find might add value, and add them. Then as you learn things about the shape of how things work, what you end up doing is rewriting them to follow your rules from what you learned.

What you'll find is, you'll have significantly better skills and systems.

It's great for feature development. It queries you about you intentions, creates a spec for you to review and modify, creates a plan for it to follow, then farms out the work to subagents.

Crap on it all you want, but it makes LLM work predictable.

It does not make LLM work predictable. Try it on the same type of project twice and see. You think you're saving time but youd accomplish similar results with 2 or 3 skills.

Which 2 or 3 skills?

I'll correct myself. 1 Skill for helping refine your plan/spec with propositional yes/no questions. After that no more skills needed to emulate superpowers honestly. Workflows do the rest and claude will do that for you. ultracode is 90% of superpowers

I think this depends a lot on two things: how well-defined your requirements are up front, and how well-defined the problem space/domain are.

If there's some clarity and structure with clear expectations, it seems to produce fairly reliable, consistent results, and the process of validating specs with Claude can yield all kinds of unexpected dead-ends or holes in the idea you had. I find this very helpful.

But I'm curious too, what are the skills you'd use instead? superpowers are just skills themselves.

How is an implementation spec that helps it author a plan to follow not considered predictable? What are these skills you are referring to specifically?

Exactly. It really is such a ridiculous waste of time

In the three years I've been vibe coding, it's the only way I've found to consistently and reliably build complex apps. How do you do it?

Three years? Vibe coding became a thing roughly 1.5 years ago, around Sonnet 4 release. How would you even compare models from 2-3 years ago to today’s? Is this satire?

> Vibe coding is a software development practice assisted by artificial intelligence (AI) where the software developer describes a project or task in a prompt to a large language model (LLM) which generates source code automatically.

Based on this definition, yep, I've been vibe coding since 2023. The products were less sophisticated, and I was copying and pasting one function at a time, but it worked. More important: it was something I couldn't do on my own.

The modern version is that bonafide engineers accept AI-generated code. It's a good thing I'm not a bonafide engineer.

That initially looked pretty interesting but a quick peek through issues and folks are complaining that it’s opinionated on git workflows and overriding user instructions otherwise. No thanks.

Edit: a deeper look at the issues and there are many examples of it not behaving as intended. Seems superstitious at best.

Definitely not superstitious. It's just an opinionated workflow, you can see the steps further down in the repository.

It's just spottily enforced because it's just written to the context in markdown - it's basically one of the very first attempts from the very beginning of Claude code.

But superstitious would mean it's just in your head, essentially - but this has an effect. It does create questionairs, documents every decision and plan etc. Wherever you want that is up to you, I personally didn't... But it's also definitely very much causing an big difference in behavior from Claude Code

Didn’t know what Superpowers was until this thread. Found this blog [0] describing how amazing Fable was at enhancing Superpowers.

[0] https://primeradiant.com/blog/2026/superpowers-6.html

This. My workflow is a heavily-modified and personalised superpowers, and the docs that it produces are an asset. I tried Fable and it just ran off and did shit. Mostly that was good shit, but not all, and I would have liked to have had some input to those decisions.

I realise this is just me needing to structure my use of Fable better. But I got to a really nice place with my Opus workflow and I'm reluctant to go through that every time a new model releases.