In this week's thrilling episode of "Captain Obvious Explores AI," our hero ponders if AI success rates decline over timeβ€”because, you know, algorithms need their beauty sleep too. πŸ’€ Meanwhile, the contact page for "deep insights" is more accessible than any actual insight in the article. πŸ“žπŸ”
https://www.tobyord.com/writing/half-life #CaptainObvious #AIExploration #AlgorithmTrends #DeepInsights #TechHumor #HackerNews #ngated
Is there a Half-Life for the Success Rates of AI Agents? β€” Toby Ord

Building on the recent empirical work of Kwa et al. (2025), I show that within their suite of research-engineering tasks the performance of AI agents on longer-duration tasks can be explained by an extremely simple mathematical model β€” a constant rate of failing during each minute a human would take

Toby Ord