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

Swarm, a new agent framework by OpenAI

github.com

Post reply on HN
Print view View original

11–20 of 113 posts

Re: Swarm, a new agent framework by OpenAI

#11

Post by mnky9800n »

antfarm wrote: post #9

There used to be another open-source agentframework by the same name, but it was for multi-agent simulations. For a moment I thought there was a new wave of interest in a deeper understanding of complex systems by means of modelling. https://en.wikipedia.org/wiki/Swarm_(simulation) https://www.santafe.edu/research/results/working-papers/the-...

I believe there is a new wave of interest in deeper understanding of complex systems through modelling and connecting with machine learning. I organized this conference on exploring system dynamics with AI which you can see most of the lectures here:

https://youtube.com/playlist?list=PL6zSfYNSRHalAsgIjHHsttpYf...

The idea was to think about it from different directions including academia, industry, and education.

Nobody presented multi agent simulations but I agree with you that is a very interesting way of thinking about things. There was a talk on high dimensional systems modelled with networks but the speaker didn't want their talk published online.

Anyways I'm happy to chat more about these topics. I'm obsessed with understanding complexity using ai, modelling, and other methods.

Re: Swarm, a new agent framework by OpenAI

#12

Post by keeeba »

mnk47 wrote: post #2

edit: They've added a cookbook article at https://cookbook.openai.com/examples/orchestrating_agents It's MIT licensed.

Thanks for linking - I know this is pedantic but one might think OpenAI’s models could make their content free of basic errors quite easily?

“Conretely, let's define a routine to be a list of instructions in natural langauge (which we'll repreesnt with a system prompt), along with the tools necessary to complete them.”

I count 3 in one mini paragraph. Is GPT writing this and being asked to add errors, or is GPT not worth using for their own content?

Re: Swarm, a new agent framework by OpenAI

#13

Post by r2_pilot »

keeeba wrote: post #12
mnk47 wrote: post #2

edit: They've added a cookbook article at https://cookbook.openai.com/examples/orchestrating_agents It's MIT licensed.

Thanks for linking - I know this is pedantic but one might think OpenAI’s models could make their content free of basic errors quite easily? “Conretely, let's define a routine to be a list of instructions in natural langauge (which we'll repreesnt with a system prompt), along with the tools necessary to complete them.” I count 3 in one mini paragraph. Is GPT writing this and being asked to add errors, or is GPT not w…

Clearly they should be using Claude instead.

Re: Swarm, a new agent framework by OpenAI

#14

Post by llm_trw »

mnky9800n wrote: post #11
antfarm wrote: post #9

There used to be another open-source agentframework by the same name, but it was for multi-agent simulations. For a moment I thought there was a new wave of interest in a deeper understanding of complex systems by means of modelling. https://en.wikipedia.org/wiki/Swarm_(simulation) https://www.santafe.edu/research/results/working-papers/the-...

I believe there is a new wave of interest in deeper understanding of complex systems through modelling and connecting with machine learning. I organized this conference on exploring system dynamics with AI which you can see most of the lectures here: https://youtube.com/playlist?list=PL6zSfYNSRHalAsgIjHHsttpYf... The idea was to think about it from different directions including academia, industry, and education. Nob…

An AI conference that isn't bullshit hype? Will wonders never cease?

> Nobody presented multi agent simulations but I agree with you that is a very interesting way of thinking about things.

To answer your question I did build a simulation of how a multi model agent swarm - agents have different capabilities and run times - would impact the end user wait time based on arbitrary message parsing graphs.

After playing with it for an afternoon I realized I was basically doing a very wasteful Markov chain enumeration algorithm and wrote one up accordingly.

Re: Swarm, a new agent framework by OpenAI

#18

Post by lrog »

llm_trw wrote: post #10
2024user wrote: post #6

What is the challenge here? Orchestration/triage to specific assistants seems straight forward.

There isn't one. The real challenge for at scale inference is that the compute for models is too long to keep normal API connections open and you need a message passing system in place. This system also needs to be able to deliver large files for multi-modal models if it's not going to be obsolete in a year or two. I build a proof of concept using email of all things but could never get anyone to fund the real deal w…

Why not use Temporal?

An example use with AWS Bedrock: https://temporal.io/blog/amazon-bedrock-with-temporal-rock-s...

Re: Swarm, a new agent framework by OpenAI

#19

Post by alchemist1e9 »

ac130kz wrote: post #17

Looks kinda poorly written: not even a single async present, print debugging, deepcopy all over the place. Such a shame that there's nothing to replace Langchain with other than writing it all from the ground up yourself.

Take a look at txtai as an alternative more flexible and more professional framework for this problem space.

Re: Swarm, a new agent framework by OpenAI

#20

Post by d4rkp4ttern »

ac130kz wrote: post #17

Looks kinda poorly written: not even a single async present, print debugging, deepcopy all over the place. Such a shame that there's nothing to replace Langchain with other than writing it all from the ground up yourself.

You can have a look at Langroid, an agent-oriented LLM framework from CMU/UW-Madison researchers (I am the lead dev). We are seeing companies using it in production in preference to other libs mentioned here.

https://github.com/langroid/langroid

Among many other things, we have a mature tools implementation, especially tools for orchestration (for addressing messages, controlling task flow, etc) and recently added XML-based tools that are especially useful when you want an LLM to return code via tools -- this is much more reliable than returning code in JSON-based tools.

Post reply on HN