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

31–40 of 117 posts

Re: HyperAgents: Self-referential self-improving agents

#31

Post by mifydev »

I've been experimenting with similar concept myself. The linter loop is the only thing that can keep the agent sane in my opinion, and if anyone can generalize bun+tsc loop to other tasks, this would finally be a way to trust LLMs output.

I was annoyed at how Claude Code ignores my CLAUDE.md and skills, so I was looking for ways to expand type checking to them. So I wrote a wrapper on top of claude-agents-sdk that reads my CLAUDE.md and skills, and compiles them into rules - could be linter rules or custom checking scripts. Then it hooks up to all tools and runs the checks. The self improving part comes if some rule doesn't work: I run the tool with the session id in review mode, it proposes the fixes and improves the rule checkers. (not the md files) So it's kinda like vibe coding rules, definitely lowers the bar for me to maintain them. Repo: https://github.com/chebykinn/agent-ruler

Re: HyperAgents: Self-referential self-improving agents

#32

Post by Jerrrrrrrry »

0xbadcafebee wrote: post #27
ilaksh wrote: post #8

Earlier quoted context omitted.

It's a feedback loop. I've always felt that the most important part of engineering was feedback loops. Maybe nature is the greatest engineer ever?

The most important part of engineering is problem-solving, which feedback loops don't necessarily do. The reason we are here as engineers is: 2.5 billion years ago, the earth made cyanobacteria, which flourished, then flooded the earth with toxic oxygen, killing almost all life on the planet. The initial feedback loop didn't solve a problem, it destroyed a use case. That's not a solution to a problem that an engineer…

Systems emerge in times of abundance, and are whittled in times of scarcity.

The great oxygenation was a time of near catyclismsic scarcity for most complex organisms, as resources scale to food/energy requirements imply the most complex organisms were the most dependent on the environment, and were most impacted by changes.

Inversely, oxygenation was our most crucial abundancy pre cursor, as it provides a large substrate chemically for life to exhibit

Re: HyperAgents: Self-referential self-improving agents

#33

Post by supermdguy »

It's surprising that this works so well considering that AI-generated AGENTS.md files have been shown to be not very useful. I think the key difference here is that the real-world experience helps the agent reach regions of its latent space that wouldn't occur naturally through autoregression.

I wonder how much of the improvement is due to the agent actually learning new things vs. reaching parts of its latent space that enable it to recall things it already knows. Did the agent come up with novel RL reward design protocols based on trial and error? Or did the tokens in the environment cause it to "act smarter"?

Re: HyperAgents: Self-referential self-improving agents

#34

Post by Jerrrrrrrry »

gobdovan wrote: post #25
Jerrrrrrrry wrote: post #7

No matter how far we go, we end up with generation / discrimination architecture. Its is the core of any and all learning/exellency; exposure to chaotic perturbations allow selection of solutions that are then generalized to further, ever more straining problems; producing increasingly applicable solutions. This is the core of evolution, and is actually derivable from just a single rule.

I don't think generation/discrimination is fundamental. A more general framing is evolutionary epistemology (Donald T. Campbell, 1974, essay found in "The Philosophy of Karl Popper"), which holds that knowledge emerges through variation and selective retention. As Karl Popper put it, "We choose the theory which best holds its own in competition with other theories; the one which, by natural selection, proves itself t…

I agree, I meant to be explicit that the one rule was "gravity";

Variation (chaos) comes from the tidal push/pull of all cumulative processes - all processes are nearly periodic (2nd law) and get slower - guaranteeing oscillator harmonics at intervals.

These intervals are astronomically convulted, but still promise a Fourier distribution of frequency: tidal effects ensure synchronization eventually, as all periods resonate eventually.

As systems are increasingly exposed to pendulums of positive and negative coherence, they will generalize for variance, and eventually for increasingly (fourier) selective filters of increasingly resiliente traits, that will generalize.

The system would eventually be increasingly resilient and eventually an awareness would develop.

Awareness of past periodic cycles would improve fitness (with or without consciousness) and eventually the mechanistic processes would be in the systems nature.

This is why we have pointless traditions, folk lore, collective unconscious artifacts, cyclical cataclysmic religions, the Fermi Paradox, the great filters...

Variation and selection are woven, but understanding how it all stems from gravity by means of nearly perioidic oscillators (spinning planets, tidal pools, celestial bodies) due to the conservation of angular momentum, due to the 3body problem.....that is what took a genius to reconcile

Re: HyperAgents: Self-referential self-improving agents

#36

Post by whattheheckheck »

lukebuehler wrote: post #19
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…

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?

Re: HyperAgents: Self-referential self-improving agents

#37

Post by whattheheckheck »

lukebuehler wrote: post #19
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…

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/

Oh wow, what do you think of karpathys autoresearch? Feels like this is just that? Gotta openclawify it?

Re: HyperAgents: Self-referential self-improving agents

#38

Post by whattheheckheck »

mifydev wrote: post #31

I've been experimenting with similar concept myself. The linter loop is the only thing that can keep the agent sane in my opinion, and if anyone can generalize bun+tsc loop to other tasks, this would finally be a way to trust LLMs output. I was annoyed at how Claude Code ignores my CLAUDE.md and skills, so I was looking for ways to expand type checking to them. So I wrote a wrapper on top of claude-agents-sdk that re…

You could try wes mckinneys roborev

Re: HyperAgents: Self-referential self-improving agents

#39

Post by whattheheckheck »

Jerrrrrrrry wrote: post #34
gobdovan wrote: post #25

Earlier quoted context omitted.

I don't think generation/discrimination is fundamental. A more general framing is evolutionary epistemology (Donald T. Campbell, 1974, essay found in "The Philosophy of Karl Popper"), which holds that knowledge emerges through variation and selective retention. As Karl Popper put it, "We choose the theory which best holds its own in competition with other theories; the one which, by natural selection, proves itself t…

I agree, I meant to be explicit that the one rule was "gravity"; Variation (chaos) comes from the tidal push/pull of all cumulative processes - all processes are nearly periodic (2nd law) and get slower - guaranteeing oscillator harmonics at intervals. These intervals are astronomically convulted, but still promise a Fourier distribution of frequency: tidal effects ensure synchronization eventually, as all periods re…

So where does gravity come from?

Re: HyperAgents: Self-referential self-improving agents

#40

Post by Atomic_Torrfisk »

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.

Post reply on HN