fractorial

How is Anthropic different? You still cannot use a subscription in a custom harness in the same way Codex allows you to.

And, no, wrapping claude -p or any other “allowed” use wherein you don’t control the agent loop isn’t the same.

I am in the process of open sourcing it! Unfortunately, my employer requires a (hopefully) cursory legal review.

I’ve rolled my own harness in Go. I have a rule to not let the production LoC exceed 50k lines. It is _very_ nice for my use cases. DeepSeek Flash V4.1 often performs at the level of GPT 5.6 Sol for non-orchestration tasks (programming and maths).

I add features and tweak it all the time: You just need to get comfortable with spending 3 hours in a chat session every 3 weeks to think hard about how to simplify whatever slop you didn’t simplify the last time you did this :)

As a programmer, maths researcher, and painter, there’s certainly something satisfying (to me) when an artistically symmetrical piece observes no mathematical symmetry: The very asymmetry in the language used to describe it is, in and of itself, beautiful.

Only under gross negligence would it be unprovable: Did you use a model whose training set included user data? Did the transcripts of any of the agents include a tool call whose result including user data?

I’m impressed you had the patience to even make it that far!

Brilliant. Precisely the reason I stopped using Anthropic's products.

Sir, I think you are lost.

> Because Codex without codex is fantastic.

Seriously: I roll my own harness over OpenRouter and GPT 5.6, and it is genuinely better than CC+Fable for my maths and programming use cases.

The one thing Fable 5.1 still tops out on is the ability to take a simple "Let's engage in an interactive complexity-removing session" and materialize abstractions and semantics quickly.

`pathological` is being used here in the security context: For example, _a parser contains a vulnerability when pathological inputs cause a program to crash._

How does a _multi-trillion dollar company_ think this is good presentation?

This is ludicrous; also, why publicly admit that blatant violation of ToS?

Roll your own harness or use an open source harness with a Codex subscription.

I maintain a Claude subscription for Fable but seldom use it.

Damn, what an epic library name.

Palomar requires the Comparator/formalization.yaml challenge stack. It also has an LLM-based vacuity gate backed by Tao.

Theoremdb is just a slop farm.

To be clear, I am deep into auto-research, but hooking up slop to slop is just unlikely to produce anything valuable.

Value is in how maths is communicated: The process, frustrations, triumphs, etc.

We have to able to take generated formalizations from “it compiles” to “it is correct” before crystallizing them.

Irrespective of opinions about a project or its authors, disclosing a potential security issue in a public forum is markedly not responsible disclosure.

This is, plainly stated, awesome.

I would love for someone to give me a coherent argument as to how this isn’t tone-deaf, vacuous garbage.

I can’t say much for a Chief Evangelist, but the Product Manager certainly has quite the C.V.

Actual link to source material: https://zenodo.org/records/21871667

It appears that there is no machine-checked proof or corroboration of this claim; I would be dubious in calling this “solved.”

Fascinating approach; however, a nightmare to scroll on mobile.

For context, I've rolled my own research harness in Go; I've been trying very hard to keep the non-test LOC around ~30k lines. To me, I consider this large, but necessary, especially after meticulously crafting red diffs while adding features.

I do use it to work on itself. I agree smaller is likely easier to work with; however, that's still, at least partly, disjoint from binary size.

I’m not quite sure why the harness itself needs to be small. Isn’t the system prompt and management of system prompt the bit you want lightweight?

I similarly find it interesting; I do not understand why it is not the default to just generate the thing as a draft, research anything you aren’t clear on, and re-write it in your own voice.

Cosmically apt username given the substance of this comment.

It would appear that rolling my own Anthropic-free harness / serving stack with a closed-weight carve out for Codex models is an absolute win.

> Do anti-LLM types expect to be vindicated in an orgy of copyright lawsuits that resets the industry back to 2022? What do people pushing expect to accomplish?

You weren’t kidding, huh.

> Google is less full of crap about the open weights stuff because of Gemma 4, but they are full of crap for a zillion other things I can't exactly feel good about them. So everyone sucks.

Google catching this stray made me laugh, ha.

Pretty much this. I designed my own research harness and infra for theorem proving and conjecturing; however, you still need to review formulations!