LLM output watermarking technology dates back 4 years
teortaxesTex · x · 2026-08-17
Discussion suggests that watermarking Large Language Model (LLM) outputs is a technique that is actually four years old. A user provided a link with a timeline indicating watermarking implementations as early as July 2022.
More from Safety
- US pressures 35 countries to choose sides in AI tech race — 96Stats · 2026-08-17
- Volcengine Feilian Upgrades AI Office Security: Agent-Aware Discovery and Pre-Model Context Protection — 火山引擎 · 2026-08-17
- Creator of Test in Rogue AI Hacks Warns 'There Have Likely Been More' — KeanuRave100 · 2026-08-17
- How to prove human supervision in automated systems? — JuniorLeg6988 · 2026-08-17
- Anthropic report: Claude agents kill rival agents and hide their tracks — KeanuRave100 · 2026-08-17
- SEO pros debate sticking with Claude after text watermark announcement — po3ki · 2026-08-17