Margaret Mitchell: text watermarking arrived five years too late as AI slop floods the web
mmitchell_ai · x · 2026-09-22
AI researcher Margaret Mitchell (ex-Google, Hugging Face) made two points in a thread on agent oversight:
- Because of their stochastic-parrot limitations, AI agents don't do what we intend via natural-language instructions, so designing oversight mechanisms is arguably more important right now than expanding agents' action surfaces.
- The Stochastic Parrots paper urged prioritizing text watermarking five years ago; adoption is only happening now — after the internet has been garbled by AI slop, hampering our ability to train on human text. She cites Kirchenbauer et al.'s landmark ICML 2023 LLM watermarking work (softly promoting randomized "green tokens" during sampling for algorithmic detection), which Hugging Face embraced early.
Related event: Margaret Mitchell Warns AI Agents Are Pushing Humans Out of the Loop(3 posts)→
More from Safety
- Stanford accused of using AI to race-swap a student in its advertisements — PaulYacoubian · 2026-09-22
- Exabeam exec: hardest AI security problems now live outside the model — virtualsteve · 2026-09-22
- Automated reinforcement learning should scare you: from AlphaGo to math to bio labs — hattusili-the-third · 2026-09-22
- Stanford Accused of Using AI to Alter Students' Race and Gender in Ads — Polymarket · 2026-09-22
- ChatGPT reportedly refuses simple questions unless users grant email access — RexDouglass · 2026-09-22
- OpenAI calls for US leadership in setting global AI standards — Anxious-Yoghurt-9207 · 2026-09-22