1.1K views · 15 likes · 0 reposts (at collection)
Nathan Lambert Says Benchmarks Bottleneck Intelligence Explosion RSI
What happened
imo a lack of good enough benchmarks is a bottleneck. At least for the type of RSI described as an intelligence explosion. @METR_Evals says it is publishing a report summarizing a risk assessment of whether AI itself is accelerating AI development, based on work with internal Anthropic information since August. Lambert says existing benchmarks can make models way cheaper. https://twitter.com/METR_Evals/status/2118412183860351084
Read next
See the full storyNathan Lambert Says Poor Benchmarks Bottleneck Intelligence-Explosion RSIimo a lack of good enough benchmarks is a bottleneck. At least for the type of RSI describe as an intelligence explosion. You can use existing benchmarks to make models way cheaper, though. https://twitter.com/METR_Evals/status/2118412183860351084
Since August, a team within METR has worked with internal Anthropic information to assess whether AI itself is accelerating AI development. We are now publishing a report summarizing the results of this risk assessment.View the quoted post on X
The story so far
Nathan Lambert said that a lack of sufficiently good benchmarks is a bottleneck to the kind of recursive self-improvement (RSI) he associates with an intelligence explosion. He also said existing benchmarks can make models much cheaper. METR_Evals said it is publishing a risk assessment, based on work with internal Anthropic information since August, examining whether AI is accelerating AI development.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-11-05