Dewi Gould

AI Safety Researcher @ArcadiaImpact

[Dewi Gould @dswg97]

@redwood_ai @ConstellOrg @MATSprogram @AetherAIS LW post: https://t.co/v9YnZFQZsr

[Dewi Gould @dswg97]

New paper!

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

@METR_Evals showed that models' time horizons have doubled every few months. We ask: what length of tasks can models complete without any CoT?

[Dewi Gould @dswg97]

Thanks to the following orgs for supporting this word: @redwood_ai @ConstellOrg @MATSprogram @AetherAIS

[Arcadia Impact @ArcadiaImpact]

*NEW* AI alignment research team!
We're announcing the new alignment team @ArcadiaImpact. A London-based team, working closely with @AISecurityInst to tackle 3 ambitious agendas in AI alignment!
👇 🧵

[🚀Henry is leading AI Safety Research Programs @sleight_henry]

🚀 Applications are now open: Constellation's Astra Fellowship 🚀

Fully funded, 5-month fellowship at our Berkeley research institute. Pair with mentors across empirical AI safety research, strategy, and governance at @ConstellOrg!

📅 Apply by May 3rd (begins Sep 2026)
🔗 https://t.co/pxtOduDBFh

[Harry Mayne @HarryMayne5]

New paper. A Positive Case for Faithfulness.

When asked to explain their decisions, LLMs can give highly plausible self-explanations. But are these explanations actually faithful, or are they just post-hoc rationalizations?

We measure faithfulness via simulatability.

[Dewi Gould @dswg97]

Big thank you to amazing collaborators @HarryMayne5 @Justinkangs and SPAR mentor @noahysiegel !

[Dewi Gould @dswg97]

New paper: A Positive Case for Faithfulness.

When asked to explain their decisions, LLMs can give highly plausible self-explanations. But are these explanations actually faithful, or are they just post-hoc rationalizations?

We measure faithfulness via simulatability.

[Dewi Gould @dswg97]

Paper: https://t.co/Dobu4iUp3x
LessWrong: https://t.co/ohsYvBaAcM