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

Autogen: Enable next-gen large language model applications

github.com

Post reply on HN
Print view View original

51–59 of 59 posts

Re: Autogen: Enable next-gen large language model applications

#51

Post by tuchsen »

TaylorAlexander wrote: post #38

This just reminds me: I have been wondering, if you get multiple instances of GPT-4 talking to each other, each seeded with a different personality prompt, do they have interesting conversations? I suspect it would devolve in to nonsense quickly, but I’ve never seen any chat log of two GPT instances talking. Does anyone have a reference for this? Thanks.

I did a DSL to facilitate this at https://prlang.com. I've had some success setting up agents to "act" out scenes, where each plays a different part, but it was kinda limited in that conversations would kinda de cohere into nonsense after a bit.

Re: Autogen: Enable next-gen large language model applications

#52

Post by wokwokwok »

a_wild_dandan wrote: post #35
wokwokwok wrote: post #21

Earlier quoted context omitted.

> a single inference is limited by context length, Yes. > multiple agents model is able to process more context at each steps of the reasoning chain What? How can a multi agent model have more context at a single step? The single step runs on a single agent. It would literally the same as a single agent? The multi agent approach is simply packaging up different “personas” for single steps; and yes, it is entirely rea…

Their comment uses two (valid) context lengths: "organizational total" and "single agent." The latter is a subset of the former. By analogy: no agent can summarize War and Peace , but several agents can, Peace-wise (sorry). Like AI map reduce. The question is thus "why not use one agent for this recursive merger?" Answers maybe being: 1. Different scholars (Russian lit. agents, ...war strategists?, etc) pay attention…

I’m not sure what this means.

Are you agreeing or disagreeing?

Yes, multiple agents with different personas will give different takes and may lead to emergent behaviour, eg. discussing the book.

Yes, they could run in parallel.

No, any single multi agent step will not have any more context than any other single step.

If you believe that the Nth prompt in a chat to a LLM eternal multiple agents has “more context” than a chat between a single agent (and itself) you don’t understand how this works.

…or you are choosing to invent your own definition of “context”.

Re: Autogen: Enable next-gen large language model applications

#53

Post by rjvs »

icandoit wrote: post #37
h4kor wrote: post #4

A question for people researching LLMs and their capabilities: Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model? I'm not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all a…

Mixture of experts: Make each model world-class within a single domain. If adding one more common-sense QnA makes the calculus-bot even slightly worse at caculus, don't do it. https://en.wikipedia.org/wiki/Mixture_of_experts

The “mixture of experts” concept in LLMs is a way of training a single model, it’s not based on training many different models (although that was the idea when the term was originally coined).

Re: Autogen: Enable next-gen large language model applications

#54

Post by ravix »

The breakthrough I've had is realizing how important it is to control the conversation between agents.

Just like in our work environments and in our relationships, HOW conversations occur largely determines the impact of the conversation. With or without AutoGen

We're building a multi-agent postgres data analytics tool. If you're building agentic software, join the conversation: https://youtu.be/4o8tymMQ5GM

Re: Autogen: Enable next-gen large language model applications

#55

Post by ProofHouse »

Tostino wrote: post #30
ugh123 wrote: post #28

Matthew Berman has a good series on AutoGen with tutorials and demos: https://www.youtube.com/watch?v=10FCv-gCKug However from his examples (and his own admission) it seems that AutoGen isn't benefitting from full GPT4-level performance even tho he's pointed it directly at OpenAPI GPT4 (and other LLMs). The back and forth between the agents does not produce great results even tho similar prompts pumped directly into…

Temperature being set differently is one culprit. There are a few hyper parameters that can be tweaked to get some pretty different output.

This is a top potential cause for sure. The variability can change drastically with temperature differences

Re: Autogen: Enable next-gen large language model applications

#56

Post by ProofHouse »

TaylorAlexander wrote: post #38

This just reminds me: I have been wondering, if you get multiple instances of GPT-4 talking to each other, each seeded with a different personality prompt, do they have interesting conversations? I suspect it would devolve in to nonsense quickly, but I’ve never seen any chat log of two GPT instances talking. Does anyone have a reference for this? Thanks.

XAgent ser

Re: Autogen: Enable next-gen large language model applications

#57

Post by ProofHouse »

lelag wrote: post #5
h4kor wrote: post #4

A question for people researching LLMs and their capabilities: Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model? I'm not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all a…

Since a single inference is limited by context length, a multiple agents model is able to process more context at each steps of the reasoning chain, which might improve the overall quality. However, given how easy it is getting to fine tune models, it's likely that multi-agent models will make a lot of sense to split the workload and assign each part to a specialized agent.

context window is fast becoming a non issue (memgpt, SPR, sink tokens etc)

Re: Autogen: Enable next-gen large language model applications

#58

Post by webappguy »

staticman2 wrote: post #18
SunghoYahng wrote: post #15

Unless I'm missing something, how is this library different from prompting a single chatbot: "Write a dialog in which A, B, and C, each playing a different role, have a conversation and do something D"?

Maybe it depends on the model but I find you'll get a different result if you say "write a dialog in which, A, B, and C talk about D" versus "read what A said and reply as B". The latter will result in each participant talking longer.

Not sure talking longer is the goal. More so, the focus and separation of each facilitates a interplay and dynamic with which an attention window on a segmented linear response (be A, B and C) cannot be individually represent nearly as rhobustly (the main inference is the primary focus). Would love to hear some other opinions chime in here.

Re: Autogen: Enable next-gen large language model applications

#59

Post by webappguy »

webappguy wrote: post #58
staticman2 wrote: post #18

Earlier quoted context omitted.

Maybe it depends on the model but I find you'll get a different result if you say "write a dialog in which, A, B, and C talk about D" versus "read what A said and reply as B". The latter will result in each participant talking longer.

Not sure talking longer is the goal. More so, the focus and separation of each facilitates a interplay and dynamic with which an attention window on a segmented linear response (be A, B and C) cannot be individually represent nearly as rhobustly (the main inference is the primary focus). Would love to hear some other opinions chime in here.

additionally, each agent can be a model using its own RAG or training data as well
Post reply on HN