We have conducted a thorough investigation into the Hugging Face incident.
We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing safeguards failed, and detail how we’re preventing recurrence.
https://t.co/hfxlbiXXiP
METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.
Have you ever tried to use @ProjectJupyter with git/@github? Did it drive you crazy because nothing worked right?
🔥It drove *us* crazy, so we fixed it.🔥
1/🧵
https://t.co/I3CeS3vRY5
Tune in now, we’re live with our #GoGet event! Hear all the amazing new products Uber has in store. Uber CEO @dkhos has the scoop. Did somebody say travel?
https://t.co/7jbPvknph4
Finally, the second edition of Interpretable Machine Learning is here! 🥳🥳🥳
So far only as e-book. Paperback should be available shortly (and in color!).
Leanpub: https://t.co/OAIEB1YNzR
Amazon: https://t.co/oeMlSUXshp
We’re excited to announce our newest and upcoming innovations that will help you GO where you want and GET what you need, easier and faster than ever before.
Check out our special event happening now! → https://t.co/wUDR0jBqaz
Uber e @CUFA_Brasil estão juntos para transportar milhares de pessoas do grupo de risco das comunidades para os postos de vacinação. Não vamos avançar até que todos possam avançar juntos 🚗 💉
Hello Brazil data lovers! Would you like to help Juvo empower over a billion underbanked people?
We're expanding our data teams in #SaoPaulo!
Get in touch if you're interested in any of our open positions: #DataScientist, #DataAnalyst, #DataEngineer.
https://t.co/sCvopZLL1E
This is mind blowing.
With GPT-3, I built a layout generator where you just describe any layout you want, and it generates the JSX code for you.
W H A T
Time to push explainable AI 🔬
exBERT, the visual analysis tool to explore learned representations from @MITIBMLab is now integrated on our model pages for BERT, DistilBERT, RoBERTa, XLM & more! Just click on the tag #exbert on @huggingface’s models page: https://t.co/zoJM9okvTW
To help developers get started with PyTorch, we’re making the 'Deep Learning with PyTorch' book, written by Luca Antiga and Eli Stevens, available for free to the community: https://t.co/KH52NW0Itl
Studies have shown that SHAP (SHapley Additive exPlanations) is the most popular machine learning interpretation tool. (read: I asked on Twitter ).
Of course, I had to learn more about it (read: I wrote a book chapter).
Here it is 🎉🎉🎉
https://t.co/nVDb731Gxs