Koby Lewis

Karma: 73

Are Persona Features Coherent?

Koby Lewis27 Oct 2026 0:08 UTC

11 points

0 comments1 min readLW link

(kobylewis.net)

Can the Assistant Axis Predict Reward-Hacking?

Koby Lewis26 Oct 2026 16:34 UTC

14 points

0 comments5 min readLW link

(jansennye.com)

You Should Think About What Needs to Go Right + My List

Koby Lewis31 Aug 2026 22:02 UTC

16 points

1 comment5 min readLW link

“Correct Answer Features” Cannot Explain Multiple Choice Capabilities

Koby Lewis30 Jun 2026 22:46 UTC

8 points

1 comment3 min readLW link

(kobylewis.net)

Porting MACHIAVELLI To Inspect

Koby Lewis17 Jun 2026 17:58 UTC

9 points

0 comments4 min readLW link

(kobylewis.net)

A Call for Better Type Hints in AI Safety Tooling

Koby Lewis28 May 2026 23:04 UTC

13 points

2 comments4 min readLW link

(kobylewis.net)

What Do You Mean by a Two-Year AGI Timeline?

Koby Lewis30 Apr 2026 1:58 UTC

6 points

1 comment1 min readLW link

Helical Representations of Turn Structure in an LLM

Koby Lewis19 Mar 2026 22:39 UTC

7 points

0 comments10 min readLW link

(kobylewis.net)