Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jononor
on Jan 5, 2024
|
parent
|
context
|
favorite
| on:
A simulation of me: fine-tuning an LLM on 240k tex...
They will RLHF* that away, as best as they can.
* Reinforcement Learning from Human Feedback
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
* Reinforcement Learning from Human Feedback