Sacks slams Anthropic-linked safety bill's 10²⁵ FLOPs frontier threshold; critics say cap capabilities, not FLOPs
jeremyakahn · x · 2026-10-18
White House AI czar David Sacks says a safety bill written with input from Anthropic is circulating on Capitol Hill, defining the frontier as models trained above 10²⁵ FLOPs (the EU's 2023 standard). He argues that as written it would eventually sweep in most of Silicon Valley and harm the startup ecosystem. jeremyakahn pushes back: worry about capabilities, not FLOPs — risks now extend to non-frontier general-purpose models, and regulation should target specific risk levels rather than model size.
More from Safety
- Miles Brundage: No AI company is secure against state attackers — Miles_Brundage · 2026-10-18
- LSCBench: top AI coding agent passes 91.3% of tests but only 25.1% ship securely — krishnan · 2026-10-18
- Aligning AI: hard engineering problem or existential threat? A three-hypothesis breakdown — sayashk · 2026-10-18
- Claude Code shows fake summarized thinking as assistant messages — ~37% of transcript — Sauers_ · 2026-10-18
- Claude helps uncover that Skipjack cipher's s-box comes from srand48(48571) — matthew_d_green · 2026-10-18
- Polymarket puts US AI safety bill odds at just 7% by end of 2026 — Polymarket · 2026-10-18