The Topology of LLM Behavior
I have this mental image that keeps coming back when I do prompt engineering. It's…
Category: Opinion
Coherent Care
I've been trying to gather my thoughts for my next tiling theorem (agenda write-up here;…
The tick in my back
It’s been almost sixteen years, I suspect, since the tick entered my body. It must…
Side by Side Comparison of RSP Versions
With all of the discussion about changes to Anthropic's Responsible Scaling Policy, I figured actually…
Anthropic and the DoW: Anthropic Responds
The Department of War gave Anthropic until 5:01pm on Friday the 27th to either give…
Ball+Gravity has a “Downhill” Preference
[epistemic status: This is a rambling thought experiment with the goal of clarifying my ontological…
Safe ASI Is Achievable: The Finite Game Argument
A few days ago, Anthropic dropped the central pledge of its Responsible Scaling Policy, the…
Best short introductions to AI safety & alignment for bright college students?
Hi, I've been asked to recommend a couple of short introductions/overviews about the key issues…
New ARENA material: 8 exercise sets on alignment science & interpretability
TLDRThis is a post announcing a lot of new ARENA material I've been working on…
3 Challenges and 2 Hopes for the Safety of Unsupervised Elicitation
Authors: Callum Canavan*, Aditya Shrivastava*, Allison Qi, Jonathan Michala, Fabien Roger(*Equal contributions, alphabetical)tl;dr: We study…