TheZvi: the 'alignment far from solved' passage is from Anthropic's PBR
TheZvi · x · 2026-10-22
Follow-up from TheZvi identifying the source of the previously quoted "Alignment is far from solved" passage: Anthropic's Public Benefit Report, with a link to the document.
Related event: Anthropic's Public Benefit Report Sparks Debate Over AI Safety Claims(3 posts)→
More from Safety
- Oracle patches Java TLS flaw CVE-2026-91403, CVSS 9.1, exploitable remotely — matthew_d_green · 2026-10-22
- Frontier labs now run millions of agents to hunt vulnerabilities — and found some — bindureddy · 2026-10-22
- Dev warns cheap open-source agents are now trivially finding low-hanging security vulns — zack_overflow · 2026-10-22
- LatePost's official X account hacked, hijacked to post adult spam — dotey · 2026-10-22
- CISO greentext: our approvals take days, the attacker's AI agent just keeps typing — zephyr_z9 · 2026-10-22
- Railway Breach: Dev Says Claude Refused to Help with Hack Response, Slams Anthropic — adamamcbride · 2026-10-22