Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
UltraSane
on Dec 25, 2024
|
parent
|
context
|
favorite
| on:
Show HN: Llama 3.3 70B Sparse Autoencoders with AP...
With the vast amounts of data LLMs are trained on they make it much easier for people to find harmful and dangerous information if they aren't filtered. See
https://en.wikipedia.org/wiki/Separation_of_isotopes_by_lase...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://en.wikipedia.org/wiki/Separation_of_isotopes_by_lase...