AI ALIGNMENT FORUM
AF

Ilya Nachevsky
000
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
No Comments Found
2Steganography via internal activations is already possible in small language models — a potential first step toward persistent hidden reasoning.
1mo
0
9Sleep peacefully: no hidden reasoning detected in LLMs. Well, at least in small ones.
5mo
0