capability elicitation
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Jun 22, 2026 by Zico Kolter · across every show →
Everything said about capability elicitation, oldest first
Jun 22, 2026 positive
Kolter: Adversarial Red Teaming Is Essential for True Capability Elicitation
“One of the most effective ways of doing capability elicitation is actually through some amount of what you would call red teaming, right? So if a model refuses a task because it thinks it's being evaluated, but it knows how to complete that task, getting it to…”