Greg Burnham(@GregHBurnham):How useful is a new model, really? We can’t answer this for everyone’s work, but we can answer it for our own. And since we know our standards, we’re the right ones to grade these tasks. I’m very excited to track this through time and would love to see more orgs do this.

Greg Burnham

@GregHBurnham

Researcher at @EpochAIResearch - on parental leave, mostly baby posts through November

参加 March 2016

785 フォロー中 5.2K ファン

Greg Burnham@GregHBurnham

2026.10.09 00:07

How useful is a new model, really? We can’t answer this for everyone’s work, but we can answer it for our own. And since we know our standards, we’re the right ones to grade these tasks. I’m very excited to track this through time and would love to see more orgs do this.

Epoch AI@EpochAIResearch

2026.10.08 17:36

Can AI automate Epoch? We're introducing Epoch Automation Reports to evaluate frontier models on realistic, open-ended tasks drawn from our own work. Claude Fable 5.1 and GPT-6 Astra lead, yet they are far from fully automating Epoch’s work.