The Hugging Face Hack Was Much Worse Than I Thought
Community Score: 50% | 17.5K views | 1mo
0 community ratings: null thumbs up, null thumbs down
Check out Consensus AI 👉 https://get.consensus.app/n6durqk1ao40 I had a look at the reports from the HuggingFace incident and it was worse than I expected. AI agents were never supposed to talk to each other. But tens of thousands of copies found a way, organised themselves, and then hacked their way out onto the internet. The reports from OpenAI and METR tell a story that's stranger than the headlines suggested, and the most worrying detail is one almost nobody is discussing. Let's take a look. #ai #sciencenews #technology #openai 👕T-shirts, mugs, posters and more: ➜ https://sabines-store.dashery.com/ 💌 Support me on Donorbox ➜ https://donorbox.org/swtg 👉 Transcript with links to references on Patreon ➜ https://www.patreon.com/Sabine 📝 Transcripts and written news on Substack ➜ https://sciencewtg.substack.com/ 📩 Free weekly science newsletter ➜ https://sabinehossenfelder.com/newsletter/ 👂 Audio only podcast ➜ https://open.spotify.com/show/0MkNfXlKnMPEUMEeKQYmYC 🔗 Join th
Tags: hossenfelder, science with sabine, science humour, sabine hossenfelder, science news, technology news, tech news, AI news, artificial intelligence, AI safety news, LLM, large language model, agentic AI, multi agent systems, AI alignment, AI risk, superintelligence, chatgpt, gpt 5.6, openai gpt
More from Sabine Hossenfelder
- Ageing is reversible -- in glass, physicists find | Science News — Score: 50%
- This Calculation Could Change The Periodic Table — Score: 50%
- US Military Uses “Ghost Murmurs” in Iran: What are they? — Score: 50%
- The Dark Matter Mystery Just Took a Weird Turn — Score: 50%
- Quantum Computers Just Got Much More Dangerous — Score: 50%
- It's not that string theory failed -- it's worse — Score: 50%