AI ALIGNMENT FORUM
AF

Nicholas Schiefer

Ω7000

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

No Comments Found

No wikitag contributions to display.

118Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

2y

69

122Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research

2y

14

37Engineering Monosemanticity in Toy Models

3y

4

6ELK Proposal - Make the Reporter care about the Predictor’s beliefs

3y

0