x

LESSWRONG

LW

Bobby Faber — LessWrong

Bobby Faber

Bobby Faber

Message

Backend/infrastructure engineer wandering into mechanistic interpretability and AI safety.

Interpretability, control, distributed systems, old poems, 4X games, experiments where nature gets to say “no,” and walls that don't actually stop anyone. GitHub

7

1

2

1mo

Bobby Faber

Backend/infrastructure engineer wandering into mechanistic interpretability and AI safety.

Interpretability, control, distributed systems, old poems, 4X games, experiments where nature gets to say “no,” and walls that don't actually stop anyone. GitHub

Hidden Knowledge? Arrr...

I tried to find hidden facts with R-Lens. [1] Then I tried the wrong facts. I used R-Lens to look for factual knowledge that Qwen wouldn’t express in ordinary chat. At first, it looked promising. On Qwen3.5-27B, R-Lens ranked words associated with benchmark facts much better than J-Lens: [2] geometric-mean...