Entropy-Preserving Reinforcement Learning
Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property…
Recent Articles
View AllHelping disaster response teams turn AI into action across Asia
AI for Disaster Response in Asia: OpenAI Workshop with Gates Foundation
I am definitely missing the pre-AI writing era
Yesterday, I wrote my first technical draft on what I was working on with the…
Claude’s constitution is great
I read Claude’s Constitution recently. I thought it was very good! This was my favourite quote:Our…
Claude has no baseline
An underappreciated LLM failure mode: not sycophancy, but cognitive state propagation. The model's critical faculties…
Sora’s shutdown could be a reality check moment for AI video
Is this just normal corporate strategy, or are we about to see a broader pullback…
Folie à Machine: LLMs and Epistemic Capture
"Truly, whoever can make you believe absurdities can make you commit atrocities." — Voltaire, 1765A…
Anthropic donations: guesses & uncertainties
tl;dr: before Anthropic IPOs, its staff won't do large-scale philanthropy. If it IPOs, its staff…
The Power of Assumption
(First real Lesswrong post! Wow. This is a post on an idea I thought might…
Parkinson’s Law of Worry
Parkinson’s law says that "Work expands so as to fill the time available for its…