🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

What is "safe" AI? Why is it difficult to achieve? Can LLMs be hacked? Are the existential risks of advanced AI exaggerated—or justified? Join us next week on Sept. 10 to hear from AI experts Karina Vold,Roger Grosse,Sedef Akinli Kocak, and Sheila McIlraith. 🔗 uoft.me/aLB

These days, the number of citations your papers get is a nonmonotonic function of their usefulness.

Is there a good history of how academic AI research came to be so focused on hill-climbing on benchmarks? Any classic essays championing this as a good way to make progress?

AI benchmarks are most useful for judging the aggregate progress of a subfield, and hence for evaluating its methodologies. And if there's one methodological lesson they've taught us, it's that the progress is made by people who aren't hill-climbing on the benchmarks!

New Anthropic research: Sabotage evaluations for frontier models How well could AI models mislead us, or secretly sabotage tasks, if they were trying to? Read our paper and blog post here: anthropic.com/research/sabot…

Announcing Transluce, a nonprofit research lab building open source, scalable technology for understanding AI systems and steering them in the public interest. Read a letter from the co-founders Jacob Steinhardt and Sarah Schwettmann: transluce.org/introducing-tr…

xAI is hiring for AI safety engineers: boards.greenhouse.io/xai/jobs/45317… Their safety agenda isn't public, so I can't judge it. However, joining as a fairly early employee could be highly impactful.

📢 The AI safety conversation continues! Check insights from last month's expert panel Karina Vold Roger Grosse Sheila McIlraith Sedef Akinli Kocak 🌐 More on the IHPST site: ihpst.utoronto.ca/news/intersect… Schwartz Reisman Institute Vector Institute Centre for Ethics Vic College UofT

Relu (yes, that ReLU), the superstar sysadmin who built the GPU servers behind AlexNet and many subsequent years of deep learning advances at U of Toronto, has left 😭 We are hiring his replacement; if you feel you could fill (or grow to fill) his big shoes, please apply!

Apply to join the Anthropic Fellows Program! This is an exceptional opportunity to join AI safety research, collaborating with leading researchers on one of the world's most pressing problems. 👇 alignment.anthropic.com/2024/anthropic…

Oh man :( We tried really hard to neither over- nor underclaim the results in our communication, but, predictably, some people drastically overclaimed them, and then based on that, others concluded that there was nothing to be seen here (see examples in thread). So, let me try

New Redwood Research (Redwood Research) paper in collaboration with Anthropic: We demonstrate cases where Claude fakes alignment when it strongly dislikes what it is being trained to do. (Thread)

New paper: We train LLMs on a particular behavior, e.g. always choosing risky options in economic decisions. They can *describe* their new behavior, despite no explicit mentions in the training data. So LLMs have a form of intuitive self-awareness 🧵