Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The LLM is the core model, but the harness has the prompts/tool definitions, guidance/recovery/correction code. The harness itself is the agent, because same model may perform vastly differently on different harnesses. Agent is the system working as a whole, harness+llm.


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

Search: