shipfeedAI news, curated daily

02:04:13 CET

pull to refreshlast sync 02:00:18

§ feed · storyline

AI leaderboards are no longer useful. It's time to switch to Pareto curves.

Apr 30 · 16:03:42 · primary fetch1 sourceupdated Apr 30 · 16:03:42

What spending $2,000 can tell us about evaluating AI agents

§ sources1 publication · timeline below

AI leaderboards are no longer useful. It's time to switch to Pareto curves. · shipfeed