Noam Brown @polynoamial

Only 2.5 years ago, AI labs would highlight their frontier LLM performance on grade school math benchmarks (GSM8K). I can't wait to see where we'll be in another 2.5 years. [引用 @_AashishReddy]: It just never gets old https://t.co/H9rsmgj99U

• AI Safety Talk Slides Into Unbelievable Claims2026-09-19