Measuring Spurious Correlations with Feature Strength

·LessWrong··

This work was partially done by an automated research scaffold developed at Redwood Research. For this project, all of the experiment ideas were designed by a human and a human wrote the write up. The AI mostly just executed on the experiment ideas. We think this project is slightly below the level of rigor of a mid-MATS research update, and the research scaffold was not very helpful for this project. More discussion of AI usage is in the Appendix.💻 CodebaseIf we want to train a classifier that...

Read full article →

Related Articles

England set to be one of the first countries to eliminate hepatitis C
stevekemp · Hacker News · 7h ago
Woman Pulled over at Gunpoint Twice After Flock Camera Glitch
cdrnsf · Hacker News · 2h ago
Stealing Reasoning Traces from Proprietary LLM APIs
quantumgarbage · Hacker News · 6h ago
Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
riordan · Hacker News · 1d ago
London Underground begins scanning passengers' faces
BlueBerry2001 · Hacker News · 10h ago