Yogesh Prabhu

Karma: 23

obsessed with interp

Can You Hide From a Natural Language Autoencoder?

Yogesh Prabhu24 Jun 2026 2:41 UTC

12 points

2 comments7 min readLW link

(yogesh.bearblog.dev)

The Dual-Use Gap

Yogesh Prabhu14 Jun 2026 17:43 UTC

5 points

2 comments4 min readLW link

(yogesh.bearblog.dev)

The Pragmatic Interpretability Trap

Yogesh Prabhu11 May 2026 4:06 UTC

8 points

0 comments3 min readLW link

(yogesh.bearblog.dev)