Jason R Brown

Karma: 617

A Conceptual Framework for Reasoning about Exploration Hacking

Jason R Brown, Nathalie Kirch, Joschka Braun, hyannakoudakis and David Lindner

8 Sep 2026 19:13 UTC

38 points

0 comments17 min readLW link

Exploration Hacking in AI Debate: Initial Empirics and Generalisation Splitting

Jason R Brown, Nathalie Kirch, Joschka Braun, hyannakoudakis and David Lindner

8 Sep 2026 19:13 UTC

33 points

0 comments13 min readLW link

A Post-Mortem for My Goal Crystallisation Project

atryt0ne and Jason R Brown

17 Jul 2026 14:30 UTC

38 points

0 comments10 min readLW link

Optimiser Choice Can Amplify or Suppress Emergent Misalignment

Jason R Brown, Patrick Leask and Lev McKinney

9 Jul 2026 10:00 UTC

63 points

2 comments4 min readLW link

Jason R Brown’s Shortform

Jason R Brown18 Jun 2026 14:26 UTC

4 points

2 comments1 min readLW link

Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask, Twm Stone, Josh Hills, Ida Caspary, Shubhorup Biswas and Julian Stastny

10 Jun 2026 17:58 UTC

280 points

23 comments4 min readLW link

Developmental Cognitive Interpretability: A Research Agenda for Modelling Generalisation and Predicting Agent Behaviour

Jason R Brown and Edward James Young

29 May 2026 9:56 UTC

70 points

0 comments7 min readLW link

AI Safety Research Futarchy: Using Prediction Markets to Choose Research Projects for MARS

Jason R Brown30 Sep 2025 15:37 UTC

37 points

10 comments4 min readLW link

TAMing The Alignment Problem

Jason R Brown7 Apr 2025 8:47 UTC

13 points

2 comments11 min readLW link

Quantifying General Intelligence

Jason R Brown17 Jun 2022 21:57 UTC

9 points

6 comments13 min readLW link