Building Effective "Agents"

(www.anthropic.com)

596 points jascha_eng | 1 comments | 20 Dec 24 12:29 UTC | HN request time: 0.212s | source

Show context

jascha_eng ◴[20 Dec 24 12:31 UTC] No.42470556[source]▶

I put the agents in quotes because anthropic actually talks more about what they call "workflows". And imo this is where the real value of LLMs currently lies, workflow automation.

They also say that using LangChain and other frameworks is mostly unnecessary and does more harm than good. They instead argue to use some simple patterns, directly on the API level. Not dis-similar to the old-school Gang of Four software engineering patterns.

Really like this post as a guidance for how to actually build useful tools with LLMs. Keep it simple, stupid.

replies(5): >>42472766 #>>42475610 #>>42475996 #>>42478651 #>>42478930 #

Kydlaw ◴[21 Dec 24 11:04 UTC] No.42478930[source]▶

>>42470556 #

In fact they are mentioning LangGraph (the agent framework from the LangChain company). Imo LangGraph is a much more thoughtful and better built piece of software than the LangChain framework.

As I said, they already mention LangGraph in the article, so the Anthropic's conclusions still hold (i.e. KISS).

But this thread is going in the wrong direction when talking about LangChain

replies(1): >>42480880 #

1. jascha_eng ◴[21 Dec 24 17:19 UTC] No.42480880[source]▶

>>42478930 #

I'm lumping them all in the same category tbh. They say to just use the model libraries directly or a thin abstraction layer (like litellm maybe?) if you want to keep flexibility to change models easily.

↑