Hacker News new | past | comments | ask | show | jobs | submit login

LLMs don't learn but agents do. You just need to insert that new knowledge in the prompt.



Agents are still LLMs. LLMs also have prompts. There's no difference!


LLMs don't have prompts, you can use prompts to query LLMs.

Agents are a mix of models, prompts, RAG and an event loop.


Agents HAVE Models. There is a big difference if you give a model access to tools and perhaps some form of memory.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: