LESSWRONG
LW

64

AlexMeinke

662100

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

No Comments Found

No wikitag contributions to display.

124Stress Testing Deliberative Alignment for Anti-Scheming Training

1mo

15

115Ablations for “Frontier Models are Capable of In-context Scheming”

10mo

1

210Frontier Models are Capable of In-context Scheming

10mo

24

68Training AI agents to solve hard problems could lead to Scheming

11mo

12

109Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

1y

37

93Apollo Research 1-year update

1y

0

57A starter guide for evals

2y

2

45Paper: Tell, Don't Show- Declarative facts influence how LLMs generalize

2y

4