Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
quickthrower2
on Aug 25, 2023
|
parent
|
context
|
favorite
| on:
Finetuning of Falcon-7B LLM Using QLoRA on Mental ...
AI could… but AI safety is a hard problem, and this particular training - I am not sure how it was done but if you just let it rip on some inputs it wont necessarily always be safe.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: