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

41–50 of 117 posts

Re: HyperAgents: Self-referential self-improving agents

#41

Post by IncreasePosts »

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.

Maybe unlock means "recognize and solve a problem with an order of magnitude fewer tokens than the first time you did it". The same way humans might spend a lot of time thinking about a certain problem and various ways to solve it, but once they go through that process, and then recognize it again, they don't need to go to the same process and jump right to the solution.

Re: HyperAgents: Self-referential self-improving agents

#42

Post by willy_k »

OutThisLife wrote: post #12
flockonus wrote: post #4

The readme seems very unclear about what it does. Anyone has a practical example of it?

Hermes agent does this, if you're curious https://github.com/NousResearch/hermes-agent

Seems like that only has the task improvement loop, no self-improvement improvement loop like this project.

Re: HyperAgents: Self-referential self-improving agents

#43

Post by zoogeny »

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…

> eventually an awareness would develop

I am not sure how this is a necessary conclusion to the premises you provide.

Re: HyperAgents: Self-referential self-improving agents

#45

Post by alexpotato »

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…

>You can get workflows that have individual parts that aren't so precise become better by composing them, and letting one component influence the other. Like e2e coding gets better by checking with "gof" tools (linters, compilers, etc). Then it gets even better by adding a coding review stage. Then it gets even better by adding a static analysis phase.

This is the exact point I make whenever people say LLMs aren't deterministic and therefore not useful.

Yes, they are "stochastic". But you can use them to write deterministic tools that create machine readable output that the LLM can use. As you mention, you keep building more of these tools and tying them together and then you have a deterministic "network" of "lego blocks" that you can run repeatably.

Re: HyperAgents: Self-referential self-improving agents

#46

Post by Jerrrrrrrry »

whattheheckheck wrote: post #39
Jerrrrrrrry wrote: post #34

Earlier quoted context omitted.

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?

A cool illusion, just another emergent property of our geometrical solution: higher dimensional aperiodic tilings of a 10^80 faceted complex polyhedra "walking" on another large aperioidic Penrose plane, that is getting smaller in a dimension we observe as "energy".

Basically a dice with a bajillion sides is getting rolled along an increasingly slim poker table, house winning eventually.

Time only goes one way, protons dont decay, energy is radiated unto the cosmic background hiss, until homogeneity is reached as CMB, and entrophy reaches 1.

I dont know where it comes from, but I know the shape it makes as it rolls by.

Re: HyperAgents: Self-referential self-improving agents

#47

Post by Jerrrrrrrry »

zoogeny wrote: post #43
Jerrrrrrrry wrote: post #34

Earlier quoted context omitted.

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…

> eventually an awareness would develop I am not sure how this is a necessary conclusion to the premises you provide.

Awareness would be any form of agency, goal seeking, or loss minimizing.

As Briggs–Rauscher reactions can eventually lead to Belousov–Zhabotinsky reactions, the system can maintain homeostasis with its environment (and continuing to oscillate) by varying reactants in a loss minimizing fashion.

This loss minimizing would be done during scarcity to limp towards an abundance phase.

This is the mechanism that hypothetical tidal pools batteries would had exhibited to continue between periods of sunlight/darkness/acidity that eventually gets stratified as a resilency trait.

Re: HyperAgents: Self-referential self-improving agents

#48

Post by sbinnee »

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 guess this paper is part of ICML coming soon this June. I hope to see a lot of cool papers.

Re: HyperAgents: Self-referential self-improving agents

#50

Post by zoogeny »

Jerrrrrrrry wrote: post #47
zoogeny wrote: post #43

Earlier quoted context omitted.

> eventually an awareness would develop I am not sure how this is a necessary conclusion to the premises you provide.

Awareness would be any form of agency, goal seeking, or loss minimizing. As Briggs–Rauscher reactions can eventually lead to Belousov–Zhabotinsky reactions, the system can maintain homeostasis with its environment (and continuing to oscillate) by varying reactants in a loss minimizing fashion. This loss minimizing would be done during scarcity to limp towards an abundance phase. This is the mechanism that hypothetica…

I'm not sure what your argument is here, except stating an opinion that loss minimization is equivalent to agency. But even if that was accepted, which is a huge stretch, it doesn't stretch all the way to awareness.
Post reply on HN