lm-watermarking: official open-source implementation of LLM text watermarks
adnan_hashmi · x · 2026-10-26
A share of the lm-watermarking GitHub repo (705 stars), the official implementation of the watermarking and detection algorithms from "A Watermark for Large Language Models" and its reliability follow-up. Includes the watermark processor, extended processor, HF Space demo, and Apache-2.0 licensing; the technique embeds statistically detectable signals into generated text to identify LLM output.
More from Safety
- If an agent can rewrite itself, does your consent still mean anything? — tallmetommy · 2026-10-26
- 109 of 529 AI Agent Incidents Involved No Adversary, Arguing Red Teams Must Test Normal Operation — anacondainc · 2026-10-26
- Cryptographer Matthew Green: if your code looks vulnerable, fix it now — matthew_d_green · 2026-10-26
- Filtering secrets on the write path: why agent memory deserves more suspicion at ingest than retrieval — Classic-Being-7960 · 2026-10-26
- After OpenCode key leak: 5 practical rules for keeping keys away from agents — jacobholm_dev · 2026-10-26
- Formal verification spat: specs are inherently limited against real-world threats — davidmanheim · 2026-10-26