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

101–110 of 117 posts

Re: HyperAgents: Self-referential self-improving agents

#101

Post by alsetmusic »

NitpickLawyer wrote: post #23
binarymax wrote: post #13

Earlier quoted context omitted.

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.

Sure. There will always be subjective tasks where the person who asks for something needs to give feedback. But even there we could come up with ways to make it easier / faster / better ux. (one example I saw my frontend colleagues do is use a fast model to create 9 versions of a component, in a grid. And they "at a glance" decide which one is "better", and use that going forwards). OTOH, there's loads you can do for…

> Things like does the site load, does it behave the same, did anything major change on the happy path, etc etc.

I asked Claude to build a web app to run locally polling data from the LAN. It fought me for four rounds of me telling it that the data from the api wasn’t rendered on the page. It created tests with mock data, it validated the api, it tested that the page loaded. It was gaslighting telling me that everything worked every time I told it that it didn’t work. I had to tell it to inspect the dom and take screenshots with Playwright to make it stop effing around. I don’t think it ever would have found the right response on its own.

Even after deliberate intervention, it regressed a few rounds later and stopped caring that tests failed. Whatever, I don’t treat it as anything more than a sometimes-correct random output machine.

Re: HyperAgents: Self-referential self-improving agents

#102

Post by internet101010 »

sva_ wrote: post #96

It appears like the 'self-improving' here just means modifying the agent's prompt/context? And not actually changing any of the weights/architecture of a model. I feel like this kind of self-improvement has some hard limits on how much it can improve.

Definitely isn't perfect and has limitations, but if the goal of predictable outcomes in a dynamic environment at scale it's more feasible than creating fine tuned models for every little thing and allows for context-based model performance benchmarking.

Re: HyperAgents: Self-referential self-improving agents

#103

Post by redanddead »

yurimo wrote: post #78

Sigh, as someone who does research in this area, this paper and its promotion on X has so many hype terms it is almost off-putting. If you read the paper what they are doing is trying to modify the scaffolding around a frozen FM until they get something better. None of this obviously includes any training (change to weights) or the underlying architecture. Even for scaffolding, a lot is still human-scaffolded: the ou…

Do you notice a lack of creativity in AI research today? What's your take

Re: HyperAgents: Self-referential self-improving agents

#105

Post by galaxyLogic »

XorNot wrote: post #86
galaxyLogic wrote: post #81

Earlier quoted context omitted.

I think Singularity is hype. What does it mean? Machines do something we can not understand? So talking about Singularity is really talking about something we can not talk about because we don't undertand what we are talking about? Wittgenstein said "From what we can not speak of, we must be silent about". That sounds like a tautology but I think there is a deeper meaning behind it. It means simply that once you star…

You got it in the third sentence and then dismissed it for some reason? That's exactly what the Singularity is: it's the transition point beyond which meaningful predictions aren't possible. In a black hole it's the center where relativity breaks down. In AI it's the point at which non-human intelligence no longer requires human intelligence for self improvement: after which predictions of the future become somewhat…

Good definitions. Would you then agree that when we reach the point where AI can improve itself without our help, it is still possible to make predictions, about it?

I think we are already in the stage where AI can and does improve itself. But why should this stage be called "Singularity"? Like a Black Hole? That sounds like hype to me.

When AI can improve itself, wouldn't it still be able to explain to us how it has improved itself? If it can not it still has a lot of improvement to do.

Or are we saying that some things are "unexplainable" and AI will discover such things without being able to explain to us what they are? That sounds like mysticism, or hype to me. Or religion. We can not explain God, right?

Re: HyperAgents: Self-referential self-improving agents

#106

Post by seertaak »

Atomic_Torrfisk wrote: post #40
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…

Im sorry, this just sounds like hypespeak. CAn you provide samples? > once they unlock one capability, What does it mean to unlock? Its an llm nothing is locked. The output is a as good as the context, model and environment. Nothing is hidden or locked.

I'll have a stab at this. I'll start with an attempt at justifying the remark that an agent which is a good coder will be good at other tasks.

1. Coding is, as a technical endeavour, relatively difficult (similarly for mathematics). So a model which performs well on this task can be expected to easily handle also-technical-but-slightly-easier tasks, like understanding (musical) harmony theory or counterpoint -- for much the same reason that human programmers/mathematicians/scientist don't struggle to understand those "easier" theories.

2. Reinforcement learning augments a base models ability to excel in something else that's "difficult", namely to "look ahead" and plan multiple steps in advance. That's literally how the training algorithm works, generating multiple paths at once, and rewarding intermediate steps in those paths which succeed in attaining the goal. And that skill, too, is extremely useful in other domains. An AI agent which learns that to break a problem into sub-problems, and then tackle each in turn methodically -- it stands to reason that it can apply that to, say, a business plan.

Note: 1 & 2 are not independent, nor are frontier models' excellence in these domains magical: it ultimately boils down to the availability of massive datasets (in particular for coding) and totally objective metrics (in the case of mathematics: solved math problems). That's the key ingrediant for reinforcement learning to be so effective.

So: the skills are transferrable because they're difficult, and require lots of planning. That models are so good at them is a fluke, and in a parallel world where humans created git repo after git repo of business plans, it might be that which we lean on to teach a reinforcement learning algorithm how to "reason" and "plan".

Now let's turn our attention to the "synergies" aspect, which I agree with. Let's say your agentic model, which is already excellent at reasoning and planning, acquires a new or improved capability which allows it to search the domain space, calculate, etc. much better than before -- this capability can now bear upon the plan, or be factored into the plan. For example, the model might be able to say "I don't need to worry about this particular subproblem for now; I can rely on my "mathematica" capability to deal with it when I absolutely need."

Or to put it differently: monkeys, like humans, are able to use (rudimentary) tools. They'll take a rock, and use it to crack open a coconut (or whatever). But a human being, with far superior reasoning and planning abilities, takes that tool, and uses it to make an even better tool -- and the result after many iterations of this process is civilization as we know it, while monkeys are still stuck trying to crack open nuts with rocks.

Re: HyperAgents: Self-referential self-improving agents

#107

Post by latentsea »

alsetmusic wrote: post #101
NitpickLawyer wrote: post #23

Earlier quoted context omitted.

Sure. There will always be subjective tasks where the person who asks for something needs to give feedback. But even there we could come up with ways to make it easier / faster / better ux. (one example I saw my frontend colleagues do is use a fast model to create 9 versions of a component, in a grid. And they "at a glance" decide which one is "better", and use that going forwards). OTOH, there's loads you can do for…

> Things like does the site load, does it behave the same, did anything major change on the happy path, etc etc. I asked Claude to build a web app to run locally polling data from the LAN. It fought me for four rounds of me telling it that the data from the api wasn’t rendered on the page. It created tests with mock data, it validated the api, it tested that the page loaded. It was gaslighting telling me that everyth…

The thing you're missing is harness engineering.

Re: HyperAgents: Self-referential self-improving agents

#108

Post by latentsea »

agrishin wrote: post #56

I found that running an agent in ralph loop, showing it the agent text and saying "run this, if it fails - identify the reason, and modify the agent instructions to avoid this, acceptance criteria are this and that" worked surprisingly well. Not sure if it qualifies as a self-referential self improving, but it was something.

I'm currently running autoresearch against my harness that autonomously builds SaaS against an enforced architecture, and autoresearch managed to improve the harness performance on my 'time-to-Realworld' benchmark which has Claude Code drive the harness to build an implementation of https://github.com/realworld-apps/realworld with the win condition that it must pass my rigorous postman collection + playwright test suites. Experiments are capped at 90 minutes and the metric it optimises for is calculated from a weighting against number of tests passing, alignment with harness engineering best practices, and time to completion.

Re: HyperAgents: Self-referential self-improving agents

#110

Post by ghywertelling »

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?

Exactly. Tools like grep, ls are also in the same category. Even in algorithm, we have techniques like memoization and Dynamic Programming which allow us to speed up things. Why should LLM fill up its context by "manually" doing what wc or ls does for you deterministically ?
Post reply on HN