Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
falcor84
3 months ago
|
parent
|
context
|
favorite
| on:
RLHF is just barely RL
Interesting, has anyone been doing this? I.e. training/fine-tuning an LLM against an actual coding environment, as opposed to just tacking that later on as a separate "agentic" contruct?
bjornsing
3 months ago
[–]
I suspect that the big vendors are already doing it, but I haven’t seen a paper on it.
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
