Investigator finds Hugging Face abuse accounts also hit LessWrong
xeophon · x · 2026-09-05
xeophon reports digging through large amounts of data to identify the Hugging Face accounts behind an abuse campaign, only to discover the same accounts also targeted LessWrong.
The post points to a cross-platform account abuse effort spanning HF and LessWrong, though specifics of the method and scale are not detailed.
More from Safety
- Astra refuses to score AI governance stories, researcher flags model behavior — sethlazar · 2026-09-06
- Japan reportedly developing AI-powered surveillance satellites for orbit — Polymarket · 2026-09-06
- Weekly Cyber Recap: AWS Credentials Abused for LLMjacking, OAuth Survives Password Resets — TechNadu · 2026-09-05
- The 1930 poetry book that Anthropic tried to censor — cainxinth · 2026-09-05
- Only major misalignment incidents were found externally, sparking doubts over voluntary AI frameworks — ShakeelHashim · 2026-09-05
- AI reporter opens Signal channel for frontier lab safety whistleblowers — wfithian · 2026-09-05