Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
garyfirestorm
27 days ago
|
parent
|
context
|
favorite
| on:
Tell HN: OpenAI keeps re-enabling the 'allow train...
Do you think the training process will retain these artifacts? I doubt it. If they were simply stealing the content - sure it would make sense - but I suspect they’re feeding it into training data and RL might distill these out.
Bluestein
27 days ago
[–]
I am thinking along these lines. You do raise a great point.-
https://www.anthropic.com/research/small-samples-poison?from...
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: