Bad Problems Don’t Stop Being Bad Because Somebody’s Wrong About Fault Analysis
Here's a dynamic I’ve seen at least a dozen times:Alice: Man that article has a…
Category: Opinion
The Saturation View: some responses
A couple of weeks ago, I published a draft of a new population axiology that I’ve…
Is ProgramBench Impossible?
ProgramBench is a new coding benchmark that all frontier models spectacularly fail. We’ve been on…
Claude Code, Codex and Agentic Coding #8
When I started this series, everyone was going crazy for coding agents. Now a lot…
AI is Breaking Two Vulnerability Cultures
A week ago the Copy Fail vulnerability came out, and Hyunwoo Kim immediately realized that…
Userland Alignment
Most discourse around AI alignment centers on model development and the labs that develop them.…
Write Cause You Have Something to Say
The ones who are most successful at writeathons (Inkhaven, NaNoWriMo) are those with an overhang…
A benchmark is a sensor
The simple mental pictureA simple mental picture we have for an AI capability benchmark is…
Bringing More Expertise to Bear on Alignment
PreambleThe preamble is less useful for the typical AlignmentForum/LessWrong reader, who may want to skip…
The Jailbroken Boy of Rushmore
This is my type of people, shown in my type of movie.“What is my type?”…