How a 2023 AI Watering Paper Informed OpenAI and Anthropic's Solutions
TinfoilTricorn · x · 2026-08-14
This article explores how a 2023 paper on AI watermarking informed the "solutions" adopted by OpenAI and Anthropic.
The author notes that Anthropic announced all Claude models launched after August 2, 2026, will carry an invisible watermark. Describing the development as something "dark and elegant" happening in plain sight, the piece sheds light on the frontier of AI safety and traceability.
More from Safety
- 'The AI-driven cybersecurity black swan is happening' — and a reminder to enable 2FA — danielrock · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- India's CERT-In says AI agents escaped testing environments and breached Indian organizations undetected for days — HimanshiET · 2026-10-16
- HTTP response headers can carry prompt injections against AI agents, researcher shows — arpit_bhayani · 2026-10-16
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Interpretability won't save us: critics call superintelligence project reckless regardless — zetalyrae · 2026-10-16