Hacker News Reader

I work on agents at Brainchain AI

I don't think they are overhyped. I think that it's easy to hook up an LLM to some functions and get impressive results, but I think to make a really good agent system there are some core pieces that need to exist around the 'agent' to enable sophisticated workloads that many are not actually building out.

Do you think AI agents are overhyped?

View on HN

I personally believe they are under-hyped, but I am struggling with tooling in the space. Feels early and barebones. Lately, I've been pushing what I can build with no-code agent platforms but all the ones I've tried are limited to DAGs, for one thing, plus a bunch of other trade-offs/limitations.

What are examples of those core pieces that need to exist?

Happy to chat offline, or please feel free to apply to Brainchain AI and you can hear all about it

Reply on news.ycombinator.com