Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
shimman
50 days ago
|
parent
|
context
|
favorite
| on:
Skills Officially Comes to Codex
Yes I'm confused as well, it feels like it's still all prompting which isn't new or different in the LLM space.
mbreese
50 days ago
[–]
It’s all just loading data into the context/conversation. Sometimes as part of the chat response the LLM will request for the client do something - read a file, call a tool, etc. The results of which end up back in the context as well.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: