Llama-agents: an async-first framework for building production ready agents

Re:Llama-agents: an async-first framework for building produ... by cheesyFish on Friday June 28, 2024 @02:41PM (#40823686)

It's definitely tough today, but its just a matter of a) using a smart LLM b) scoping down individual agents to a manageable set of actions

As more LLMs come from companies and open-source, their reasoning abilities are only going to improve imo.

[ Parent | on HN ]

Re:Llama-agents: an async-first framework for building produ... by k__ on Friday June 28, 2024 @03:27PM (#40824248)

I hope this will improve.

Right now the products I see are just junior level software with an LLM behind.

[ Parent | on HN ]

Re:Llama-agents: an async-first framework for building produ... by m_a_u on Friday June 28, 2024 @03:40PM (#40824417)

For me it's a difficult field. The thoughts "I could have written this myself, but maybe better" and "I will never understand this" occur with similar frequencies

[ Parent | on HN ]