by hubraumhugo on 10/12/24, 5:07 PM
Has anyone seen AI agents working in production at scale? It doesn't matter if you're using Swarm, langchain, or any other orchestration framework if the underlying issue is that AI agents too slow, too expensive, and too unreliable. I wrote about AI agent hype vs. reality[0] a while ago, and I don't think it has changed yet.
[0] https://www.kadoa.com/blog/ai-agents-hype-vs-reality
by antfarm on 10/12/24, 10:44 AM
by ac130kz on 10/12/24, 12:04 PM
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.
by mnk47 on 10/12/24, 12:05 AM
by segmondy on 10/12/24, 2:20 PM
There's absolutely nothing new in this framework that you won't find in a dozen other agent frameworks on github.
by kgc on 10/12/24, 6:14 PM
I feel like there's a motivation here to generate a lot of inference demand. Having multiple o1 style agents churning tokens with each other seems like a great demand driver.
by sebnun on 10/12/24, 4:31 PM
I immediately thought of Docker Swarm. Naming things is one of the hardest problems in computer science.
by Quizzical4230 on 10/12/24, 1:35 PM
by nsonha on 10/12/24, 9:33 AM
how does this compare to Autogen and LangGraph? As someone new to this space, I tried to look into the other 2 but got pretty overwhelmed. Context is making multi agents, multi steps reasoning workflows
by arach on 10/12/24, 11:54 PM
Worth noting there is an interesting multi-agent open source project named Swarms. When I saw this on X earlier I thought maybe the team had joined OpenAI but there's no connection between these projects
> "Swarms: The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework"
[0] https://github.com/kyegomez/swarms
[1] https://docs.swarms.world/en/latest/
by ItsSaturday on 10/12/24, 10:22 AM
" 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!)"
Nope this doesn't mean it at all. You decided additionaly and independent from the other statements that you do not allow collaboration at all.
Which is fine the sentence is still unlogical
by 2024user on 10/12/24, 9:50 AM
What is the challenge here? Orchestration/triage to specific assistants seems straight forward.
by siscia on 10/12/24, 12:33 PM
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.)
by thawab on 10/12/24, 11:54 AM
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?
by htrp on 10/12/24, 12:32 PM
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?
by sidcool on 10/13/24, 12:21 PM
ELI5 anyone?
by nobrains on 10/12/24, 7:39 AM
It is a foreshadowing name...