Iterated Development and Study of Schemers (IDSS)
Published on October 10, 2025 2:17 PM GMTIn a previous post, we discussed prospects for…
Category: Opinion
You should probably prepare for your chats to be fed to AI
Published on October 10, 2025 11:20 AM GMTHere's some things to keep in mind as…
Assuring Agent Safety Evaluations By Analysing Transcripts
Published on October 10, 2025 12:42 AM GMTSummaryThis is a research update from the Science…
Labs lack the tools to course-correct
Published on October 10, 2025 4:10 AM GMTThis post is part of the sequence Against…
At odds with the unavoidable meta-message
Published on October 10, 2025 12:13 AM GMTIt is a truism known to online moderators[1] that…
Stars are a rounding error
Published on October 9, 2025 11:35 PM GMTNotes on some interesting factoids I learnt from…
Towards a Typology of Strange LLM Chains-of-Thought
Published on October 9, 2025 10:02 PM GMTIntro LLMs being trained with RLVR (Reinforcement Learning…
Training Qwen-1.5B with a CoT legibility penalty
Published on October 9, 2025 9:33 PM GMTI tried training Qwen2.5-1.5B with RL on math…
Interview with a drone expert on the future of AI warfare
Published on October 9, 2025 8:16 PM GMTA conversation with Paul Scharre, author of Four…
Investigating Neural Scaling Laws Emerging from Deep Data Structure
Published on October 9, 2025 8:11 PM GMTThis is a summary of the project I…