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

Show HN: Microagents: Agents capable of self-editing their prompts / Python code

github.com

Post reply on HN
Print view View original

51–60 of 82 posts

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#51

Post by sparrowInHand »

bob1029 wrote: post #30

I built a few multi agent systems and went down a rabbit hole where I reached an important conclusion - From the perspective of the LLM, the prompt/context is the only thing that ever matters. Everything about how your agent will behave ultimately boils down to this. I had a bunch of fancy stuff like agents collaborating by passing messages and interpreting them with their own prompts and function calls. Then I reali…

Maybe the LLM needs something like dantes Divina Commedia as previous instances describe in condensed forms why a previous prompts conclussions failed, to succesfully navigate around the trained in local minimas. I diary of failure to keep track on how to reach a success.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#52

Post by travisjungroth »

wg0 wrote: post #32
travisjungroth wrote: post #20

Earlier quoted context omitted.

That's not a fitting analogy because there is no equivalent to the laws of thermodynamics that says a system can't be self improving. You're dismissing a technological possibility without much reason. We are extremely similar genetically to our ancestors of 100k years ago. The big difference is cultural inheritance. We come up with ideas and objects and pass them down. Humans have improved the capabilities of humans.…

Now you're falsely equating biological brains with giant arrays of floating point numbers. we have NOT evolved where we are today by generating inputs to ourselves, watching our own output and modifying our inputs to watch again our outputs. Rather - we had fundamental strong reasoning almost flawless rigorous (formally documented) capabilities from the get go. Interference, induction, deduction. LLMs have none of th…

> Rather - we had fundamental strong reasoning almost flawless rigorous (formally documented) capabilities from the get go.

What are you talking about? This doesn't describe the vast majority of human knowledge.

You're dismissing the possibility of new technology via a real loose analogy and insulting anyone who disagrees. This isn't what good reasoning looks like.

GANs already exist. The linked project already exists.

> A model will generate its own input and will watch it's own output and in process, will become more intelligent than it really is.

If you sub out the needless contradiction of "more intelligent than it really is" for "more intelligent than it was", then this is something that already happens. It will continue to happen whether you believe in it or not.

You're acting like you're arguing against people with sketches of perpetual motion devices. You're not. This is like arguing against heavier-than-air flight in 1905. You are way behind.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#53

Post by travisjungroth »

geraneum wrote: post #50
Cyphase wrote: post #42

Earlier quoted context omitted.

> There’s no evidence that today’s human is cognitively more capable than their human ancestors. It’s a conflation of technology and transference of knowledge with intelligence. That was their point. See here: > We are extremely similar genetically to our ancestors of 100k years ago. The big difference is cultural inheritance. We come up with ideas and objects and pass them down.

Yup, hence the “unfit” analogy. It doesn’t correspond well with LLMs getting more intelligent in the same way, which I believe, is intended by having a “self editing agent”.

In the linked project, the LLM edits its prompt. I think this is similar enough to humans improving our capabilities through ideas (such as language) that it counters the complete dismissal LLMs improving themselves as if it violated the laws of thermodynamics.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#54

Post by clbrmbr »

mitthrowaway2 wrote: post #5
PrayagBhakar wrote: post #3

Earlier quoted context omitted.

But isn’t this also a step towards AGI? The model being able to find issues and self correct?

As described in the essay "optimality is the tiger, and agents are its teeth". https://www.lesswrong.com/posts/kpPnReyBC54KESiSn/optimality...

From the linked LW post:

> It is doing this for no greater reason than that an optimiser was brought into reach, and this is what optimisers do.

> All the agent piece has to do is pump the optimality machine.

It’s like putting the mic too close to the amplifier.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#55

Post by wg0 »

travisjungroth wrote: post #52
wg0 wrote: post #32

Earlier quoted context omitted.

Now you're falsely equating biological brains with giant arrays of floating point numbers. we have NOT evolved where we are today by generating inputs to ourselves, watching our own output and modifying our inputs to watch again our outputs. Rather - we had fundamental strong reasoning almost flawless rigorous (formally documented) capabilities from the get go. Interference, induction, deduction. LLMs have none of th…

> Rather - we had fundamental strong reasoning almost flawless rigorous (formally documented) capabilities from the get go. What are you talking about? This doesn't describe the vast majority of human knowledge. You're dismissing the possibility of new technology via a real loose analogy and insulting anyone who disagrees. This isn't what good reasoning looks like. GANs already exist. The linked project already exist…

> What are you talking about? This doesn't describe the vast majority of human knowledge.

I hope you don't mean to say that vast majority of knowledge is devoid of any consistent reasoning and is just hallucinated on the way as an LLM does.

> It will continue to happen whether you believe in it or not.

We'll see. I believe post transformers, next AI winter is around the corner - for a while.

What I see above is an LLM chewing its own output with light modifications as input and that's not going to lead anywhere as the README of the project itself clearly notes. It gets stuck.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#56

Post by regularfry »

bob1029 wrote: post #30

I built a few multi agent systems and went down a rabbit hole where I reached an important conclusion - From the perspective of the LLM, the prompt/context is the only thing that ever matters. Everything about how your agent will behave ultimately boils down to this. I had a bunch of fancy stuff like agents collaborating by passing messages and interpreting them with their own prompts and function calls. Then I reali…

That's true if you're passing messages between identical models. There's a question to ask as to whether different models trained for different tasks would be better than single, multipurpose models though. My gut feel is that eventually multipurpose models will win because you don't have the embedded cost of relearning what syntactic structure is, but for a given training time and number of weights it's not clear whether that's true today.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#57

Post by regularfry »

jumploops wrote: post #14

We do something similar with Magic Loops[0], but within the context of generating a single "loop" (automation). We've found that LLMs are pretty bad at prompting other LLMs, unless the problem at hand is very limited in scope. It's too easy to get incorrect/expensive behavior otherwise (e.g. starts building a framework against an imaginary API, instead of using an existing tool). Our approach looks more like a state…

One interesting detail in the Code As Policies paper from last year was that they generate code from the given API, then recursively get the LLM to implement any functions from what it generates that don't already exist. I thought that was quite neat.

I've started seeing those sort of hallucinated API calls as a signal for something that ought to exist; if it's predictable enough for an LLM to think it might, then maybe it should, to make it easier for humans too?

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#58

Post by Palmik »

wg0 wrote: post #32
travisjungroth wrote: post #20

Earlier quoted context omitted.

That's not a fitting analogy because there is no equivalent to the laws of thermodynamics that says a system can't be self improving. You're dismissing a technological possibility without much reason. We are extremely similar genetically to our ancestors of 100k years ago. The big difference is cultural inheritance. We come up with ideas and objects and pass them down. Humans have improved the capabilities of humans.…

Now you're falsely equating biological brains with giant arrays of floating point numbers. we have NOT evolved where we are today by generating inputs to ourselves, watching our own output and modifying our inputs to watch again our outputs. Rather - we had fundamental strong reasoning almost flawless rigorous (formally documented) capabilities from the get go. Interference, induction, deduction. LLMs have none of th…

> we have NOT evolved where we are today by generating inputs to ourselves

Sure, we have not evolved this way in the strictly biological sense, but we did greatly extend our capabilities this way. The jump in capabilities in the past tens of thousands of years is mostly from passing knowledge around and incrementally building on top of it. Often by building higher level abstractions, and building more complex systems on top of those, or by dividing the problem into distinct parts, and having people specialize.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#59

Post by travisjungroth »

wg0 wrote: post #55
travisjungroth wrote: post #52

Earlier quoted context omitted.

> Rather - we had fundamental strong reasoning almost flawless rigorous (formally documented) capabilities from the get go. What are you talking about? This doesn't describe the vast majority of human knowledge. You're dismissing the possibility of new technology via a real loose analogy and insulting anyone who disagrees. This isn't what good reasoning looks like. GANs already exist. The linked project already exist…

> What are you talking about? This doesn't describe the vast majority of human knowledge. I hope you don't mean to say that vast majority of knowledge is devoid of any consistent reasoning and is just hallucinated on the way as an LLM does. > It will continue to happen whether you believe in it or not. We'll see. I believe post transformers, next AI winter is around the corner - for a while. What I see above is an LL…

It's certainly not "almost flawless rigorous (formally documented) capabilities".

> We'll see.

I guess people could just... stop. Seems unlikely. Again, you're saying that something already happening is impossible.

Re: Show HN: Microagents: Agents capable of self-editing their prompts / Python code

#60

Post by quasiuna »

I've been experimenting with something in a similar space with JavaScript called "Paint AI" https://paintai.groupmind.co.uk

Here I've created a basic Paint program with no pens, brushes or other drawing tools. Instead you get the AI to create the painting tools for you and it writes, tests and deploys the JavaScript for you live, usually within 30 seconds.

It only uses OpenAI's gpt-3.5-turbo model too which is fast and good enough for this use case.

Post reply on HN