eggsyntax

Karma: 1,727

AI safety & alignment researcher

Show, not tell: GPT-4o is more opinionated in images than in text

Daniel Tan and eggsyntax

Apr 2, 2025, 8:51 AM

103 points

41 comments3 min readLW link

Numberwang: LLMs Doing Autonomous Research, and a Call for Input

eggsyntax and ncase

Jan 16, 2025, 5:20 PM

71 points

30 comments31 min readLW link

LLMs Look Increasingly Like General Reasoners

eggsyntaxNov 8, 2024, 11:47 PM

94 points

45 comments3 min readLW link

AIS terminology proposal: standardize terms for probability ranges

eggsyntaxAug 30, 2024, 3:43 PM

30 points

12 comments2 min readLW link

LLM Generality is a Timeline Crux

eggsyntaxJun 24, 2024, 12:52 PM

218 points

119 comments7 min readLW link

Language Models Model Us

eggsyntaxMay 17, 2024, 9:00 PM

158 points

55 comments7 min readLW link

Useful starting code for interpretability

eggsyntaxFeb 13, 2024, 11:13 PM

26 points

2 comments1 min readLW link

eggsyntax’s Shortform

eggsyntaxJan 13, 2024, 10:34 PM

3 points

165 comments LW link