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

21–30 of 113 posts

Re: Swarm, a new agent framework by OpenAI

#21

Post by llm_trw »

lrog wrote: post #18
llm_trw wrote: post #10

Earlier quoted context omitted.

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...

Because when you see someone try and reinvent Erlang in another language for the Nth time you know you can safely ignore them.

Re: Swarm, a new agent framework by OpenAI

#22

Post by dartos »

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.

I hold no love for openai, but to be fair (and balanced) they put this right in the start of their readme.

> Swarm is currently an experimental sample framework intended to explore ergonomic interfaces for multi-agent systems. It is not intended to be used in production, and therefore has no official support. (This also means we will not be reviewing PRs or issues!)

It’s literally not meant to replace anything.

IMO the reason there’s no langchain replacement is because everything langchain does is so darn easy to do yourself, there’s hardly a point in taking on another dependency.

Though griptape.ai also exists.

Re: Swarm, a new agent framework by OpenAI

#24

Post by siscia »

I am not commenting on the specific framework, as I just skimmed the readme.

But I find this approach working well overall.

Moreover it is easily debuggable and testable in isolation which is one of the biggest selling point.

(If anyone is building ai products feel free to hit me.)

Re: Swarm, a new agent framework by OpenAI

#25

Post by htrp »

thawab wrote: post #15

In the example folder they used qdrant as a vector database, why not use openai’s assistants api? The idea for a vendor lock solution is to make things simpler. Is it because qdrant is faster?

qdrant is part of the openai tech stack for their RAG solutions

Re: Swarm, a new agent framework by OpenAI

#26

Post by exitb »

htrp wrote: post #23

Does anyone else feel like these are Google-style 20% time projects from the OpenAI team members looking to leave and trying to line up VC funding?

Doesn’t working on a venture on company time put you at an enormous disadvantage in terms of ownership?

Re: Swarm, a new agent framework by OpenAI

#29

Post by 2024user »

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…

Thanks. Could something like Kafka be used?

Re: Swarm, a new agent framework by OpenAI

#30

Post by arnaudsm »

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.

OpenAI's code quality leaves to be desired, which is surprising considering how well compensated their engineers are.

Their recent realtime demo had so many race conditions, function calling didn't even work, and the patch suggested by the community hasn't been merged for a week.

https://github.com/openai/openai-realtime-api-beta/issues/14

Post reply on HN