Event Dime

Building Better Activation Oracles

Family & Kids
When:
June 4, 2026 · 6:34 PM
Source:
A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong

Work done for our MATS 10.0 Sprint project - mentored by Neel Nanda and Adam Karvonen Huggingface, Github TL;DR: We have improved the original Activation Oracle (AO) training regime by training on on-policy rollouts, improving the conversational dataset, feeding more layers (following the approach by Niclas Luick ) and making a small change to the injection formula. We also open source our evals, which we believe are currently the most comprehensive evaluation of AO quality called AObench. The c

Why this event appears here

This listing is shown because it is tied to the current city coverage and carries structured metadata that can be indexed and compared with other events.

  • City coverage

    Local event

  • Primary source

    A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong

  • Categories

    Family & Kids