Henning B

Message

Nurturing the best AI safety talent as a Research Manager at MATS!

Previously worked as AI developer in speech recognition and gen AI for 3 years. Pursued part-time technical safety research (2021-24), and coaching for career impact and personal growth (since 2017).

The Elicitation Game: Evaluating capability elicitation techniques

We are releasing a new paper called “The Elicitation Game: Evaluating Capability Elicitation Techniques”. See tweet thread here. TL;DR: We train LLMs to only reveal their capabilities when given a password. We then test methods for eliciting the LLMs capabilities without the password. Fine-tuning works best, few-shot prompting and prefilling...

Feb 27, 202510

AI ALIGNMENT FORUM
AF

AI ALIGNMENT FORUM
AF

Henning B

Henning B

Henning B

Henning B

The Elicitation Game: Evaluating capability elicitation techniques

The Elicitation Game: Evaluating capability elicitation techniques