Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

HyperAgents: Self-referential self-improving agents

github.com

Post reply on HN
Print view View original

91–100 of 117 posts

Re: HyperAgents: Self-referential self-improving agents

#91

Post by menaerus »

adw wrote: post #24
ghywertelling wrote: post #11

Earlier quoted context omitted.

What are the differences wrt Recursive Language Models

Completely unrelated. Recursive Language Models are just "what if we replaced putting all the long text into the context window with a REPL which lets you read parts of the context through tool calls and launch partitioned subagents", ie divide-and-conquer applied to attention space.

My first thought was also that this is also reminiscent of RLMs - they are ought to solve the same problem as far as my understanding goes. Authors say "Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes" which is what RLM is trying to solve so my understanding is that this work shares the same goal but takes a different approach. E.g. instead of using REPL-like environment with multiple (or even single) agents, which is what RLMs are doing, they suggest using agents that can modify themselves. I didn't read the paper so I don't know how this really works but it caught my attention so if you could share more insights I would appreciate it.

Re: HyperAgents: Self-referential self-improving agents

#97

Post by d0963319287 »

binarymax wrote: post #13
NitpickLawyer wrote: post #9

The paper is here - https://arxiv.org/pdf/2603.19461 This, IMO is the biggest insight into where we're at and where we're going: > Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. There's a thing that I've noticed early into LLMs: once they unlock one capability, you can use that capability to compose stuff and improve on oth…

I disagree that evaluation is always a coding task. Evaluation is scrutiny for the person who wants the thing. It’s subjective . So, unless you’re evaluating something purely objective, such as an algorithm, I don’t see how a self contained, self “improving “ agent accomplishes the subjectivity constraint - as by design you are leaving out the subject.

[flagged]

Re: HyperAgents: Self-referential self-improving agents

#99

Post by cestivan »

iamandoni wrote: post #65
lukebuehler wrote: post #19

Earlier quoted context omitted.

Agree. It's code all the way down. The key is to give agents a substrate where they can code up new capabilities and then compose them meaningfully and safely. Larger composition, though, starts to run into typical software design problems, like dependency graphs, shared state, how to upgrade, etc. I've been working on this front for over two years now too: https://github.com/smartcomputer-ai/agent-os/

> Larger composition, though, starts to run into typical software design problems I've been seeing the same thing. Where agents are great solving the immediate task, but as changes compound they run into software & architectural design problems. I created https://github.com/andonimichael/arxitect to help at least have coding agents self reflect on their software design. But I really like your approach to self-modific…

[dead]

Re: HyperAgents: Self-referential self-improving agents

#100

Post by lukebuehler »

whattheheckheck wrote: post #36
lukebuehler wrote: post #19

Earlier quoted context omitted.

Agree. It's code all the way down. The key is to give agents a substrate where they can code up new capabilities and then compose them meaningfully and safely. Larger composition, though, starts to run into typical software design problems, like dependency graphs, shared state, how to upgrade, etc. I've been working on this front for over two years now too: https://github.com/smartcomputer-ai/agent-os/

So what are software packages now a days other than precomputed subsets of capabilities. Like a mesh that data gets pushed through to produce what? What are the optimal subset of prebuilt programs to accomplish any task?

It's a tradeoff. Technically, you need very few programs, you can let an agent do everything and coordinate everything. But that is also inefficient, it's slow and uses a lot of tokens. So you allow the agent to build tools and coordinate those tools, just like we humans do. However, with agents, the threshold of pain is much higher, we can let agents do thing's "manually" where humans would build automations much sooner.
Post reply on HN