Posts
2024
Notes from the 6th Athens Roundtable on AI Governance
December 13, 2024
Evals best practices from Apollo's co-founder
December 6, 2024
How to make evals for the AISI evals bounty
December 3, 2024
Recovering the underlying SAE vectors from Goodfire's API
November 26, 2024
Books I've Read in October
November 26, 2024
VC Spotlight with Juniper Ventures
November 25, 2024
Notes from a talk with the Singapore AI Safety Institute
November 16, 2024
I tried a colour walk
November 14, 2024
Scattered thoughts on what it means for an LLM to have beliefs
November 6, 2024
Definitions are over-rated in EA
November 6, 2024
My first taste of debating
November 3, 2024
AI as a powerful meme, via CGP Grey
October 30, 2024
An intuitive understanding of logits and softmax via log-odds
October 26, 2024
Recommended blogposts and podcasts for AI Safety
October 24, 2024
Learnings from running five 1.5-hour ice-breakers
October 24, 2024
Insights from AISI, OpenAI, and The Future Society
October 11, 2024
Creating this new website
October 9, 2024
2022
Outer and Inner Misalignment
April 27, 2022