Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
retinaros
80 days ago
|
parent
|
context
|
favorite
| on:
Anthropic says Alibaba illicitly extracted Claude ...
they even published papers where they distill gpt models…
https://alignment.anthropic.com/2025/subliminal-learning/
anthropic is really adversarial.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://alignment.anthropic.com/2025/subliminal-learning/
anthropic is really adversarial.