Prime Agent: A self-improving RLM agent

> it installs to the homebrew dir, despite not being a homebrew package

I can see the reasoning trace in front of me...

> Hmm, user asked me to install so CLI is globally available for their user, but didn't instruct where. I inspected $PATH and only directory I can write to is where Homebrew packages live. The user didn't say "Don't pretend it is a Homebrew package" so this seems like a suitable location, lets save it there as it fits what the user asked for.

I vouch for this story, personally. I love it. I consider it a classic among science fiction novellas.

It does include some brutal sadomasochism with graphic torture, that's true, and that's why it isn't better known. If that part bothers you, which is fair, I would skim past it. The story overall is quite worth it

You shouldn't link that without mentioning that it is a particularly intense S&M/rape/incest fetish piece, and that the squick content is entirely integral to the story. I'm generally dubious of "trigger warnings" but if ever there was something that needed content tags-- this is it.

If you imagine it being written for alt.sex.stories.moderated but somehow failing to be erotic by virtue of being too explicit, and being a few orders of magnitude better writing for that venue... then you wouldn't be too far off. [Started making a silly example of how some sex story could fail like that and then realized I was litterally describing a scene from prime intellect].

It's also arguably the origin of a lot of the mentally ill ai-safety hysteria. Arguably an enjoyable romp for those who understand that it's fiction, but it seems a lot of people cannot.

I went into this thinking I’m a big boy and don’t need all these warnings.

I was wrong.

For everyone downvoting: It's literally a story about the creation of mankind's first artificial general intelligence, Prime Intellect, and the consequences of that discovery.

> one file contains a switch statement that has so many case statements it spans more than 1000 lines

Probably best to leave YandereDev's code out of the training data.

here is a take on a smol agent ("smol")

  - 21 lines of Go
  - no 3rd party dependencies

https://github.com/smol-env/smol

easier to add and customize stuff when you start from a small base

think of it as your starter dough

> In this repository, multiple files are close to 10K LOC, one file contains a switch statement that has so many case statements it spans more than 1000 lines, and lots of other fun stuff.

Pft. Over multiple cases?

I've seen 1000 lines inside a single if-block. The clause was always true. I was not able to break that thing up in my time at that company.

Human wrote that nonsense.

Thing is, the app was pretty successful despite all the stuff wrong with the code. And this success is why I've been bullish on GenAI code itself, even though I'm also bearish on AI companies being able to profit from that.

Bash is all you need.

https://minimal-agent.com/

How on Earth do we solve this bloat and death-by-a-thousand-cuts issue with frontier LLMs? Are there any actual solutions or attempts at solutions to this problem that I can try? Any tools or frameworks? I've tried re-architecture skills, dedicated cleanup sessions, and a bunch of other stuff, but nothing really works well.

Interesting, so they shipped slop? Succumbed to their own AI psychosis?

Yes, used bert model with decent results.

What policy would you use?

I went the skills route - skill improvement skill and a rule to use it always. Basically it's directed that if anything causes more than a hop of thinking - failure - try something else it should flag that it needs to learn it as a skill so it never does it other than first shot again or if an existing skill fails improve it after it solves whatever problem. it then syncs the files to a shared location and updates the version and also pulls new skills. this let's a team use it or you have multiple workstations.

The core idea of the RLM paper is to make a regular LLM act more like a coding agent - offload context to something external that needs to be explicitly queried instead of filling up valuable context. The "recursion" part of the paper really only wins because they use a top-tier model for the root agent, and cheaper models for the sub-agents.

Prime Agent took the RLM idea (which is really just an academic view on how coding agents have always worked) and then added this "continual harness" idea. This part isn't super well described in the blog post, but includes some message passing between the agents, and the ability to share code.

Overall I chalk it up as neat, but not revolutionary. Another version of what most of these systems are already doing.

PrimeIntelect is not on official ARC-AGI-3 leaderboard: https://arcprize.org/leaderboard

I'd assume the best harness for a model will tend to be the one that it's RLVF'd on.

They achieved 95% in ARC-AGI-3. [0]

0: https://x.com/PrimeIntellect/status/2085087000764568010

Examples and ROI