AI Safety Radar
Wednesday, 11 November 2026

Research / Sources

LessWrong

AI research and discussion on LessWrong. www.lesswrong.com

Focus All
Topic Evals

Pick up to 2: papers tagged with all of them

Date Any time
27 Mar 2025BlogEvals, Agents

What is scaffolding?

An AISafety.info explainer defining LLM scaffolding, its common types, and why scaffolding matters for dangerous-capability evaluations and for interpretability of LLM reasoning.

AI "Agent" ScaffoldsAI
24 Mar 2025BlogEvals

Analyzing long agent transcripts (Docent)

Transluce presents Docent, a tool for analysing long AI agent transcripts to find corrupted tasks, scaffolding bugs and unexpected behaviours, showing a fixed environment raised GPT-4o's InterCode solve rate.

AI "Agent" ScaffoldsAI