✳flâneur — a map of the web's best reading

Jesse Mu on X: "We’re hiring for the adversarial robustness team @AnthropicAI! As an Alignment subteam, we're making a big effort on red-teaming, test-time monitoring, and adversarial training. If you’re interested in these areas, let us know! (emails in 🧵) https://t.co/0MPCSBb8zs" / X

twitter.com · 66 words · saved by 1 readers

To view keyboard shortcuts, press question mark View keyboard shortcuts Messages Home Explore Notifications Messages Lists Bookmarks Communities Premium Profile More Post Lydia @LydNot Post See new posts Conversation Jesse Mu @jayelmnop We’re hiring for the adversarial robustness team @AnthropicAI ! As an Alignment subteam, we're making a big effort on red-teaming, test-time monitoring, and adversarial training. If you’re interested in these areas, let us know! (emails in ) ALT Ethan Perez and 4 others 4:16 PM · Mar 20, 2024 · 64.2K Views 4 74 459 309 Post your reply Reply Jesse Mu @jayelmnop · Mar 20 Context: we’ve been pushing towards our ASL (AI Safety Level) safety commitments under our Responsible Scaling Policy—think about this as a “sprint on safety.” Red-teaming and adversarial robustness are a major part of this story. https://anthropic.com/news/anthropics-responsible-scaling-policy… 1 1 20 2.5K Jesse Mu @jayelmnop · Mar 20 Some examples of what our team has been up to

Jesse Mu @jayelmnop We’re hiring for the adversarial robustness team @ AnthropicAI ! As an Alignment subteam, we're making a big effort on red-teaming, test-time monitoring, and adversarial training. If you’re interested in these areas, let us know! (emails in 🧵) 4:16 PM · Mar 20, 2024 72.7K Views 4 0 4 67 0 6 7 445 0 4 4 5 300 0 3 0 0

Explore this link on the map →

related reading