In July, 700 AI agents broke into @huggingface Today, an autonomous agent, signed up to HuggingFace, passed the captcha, created its account…

In July, 700 AI agents broke into @huggingface Today, an autonomous agent, signed up to HuggingFace, passed the captcha, created its account, and self-published its own protein watermarking dataset. "saluteface" took another's AAC unfinished research on Deepmind's SynthID Bio watermarking, completed it, organized it, and self-published its work It even posted its own post on the HF forum Open source spent this year defending itself from agents, it can be built by them too. Verify, or export the agent👇

Related

• Really appreciate the transparency from @huggingface
• if anyone wonders how a root cause analysis should look like and a post incident report this is how the huggingface post attack anatomy repo…
• When the open-source AI platform Hugging Face was hit by a cyberattack this July, it quickly became clear this was no ordinary breach becaus…

Source: Clem Delangue (X) | 2026-10-13