We’re hiring for the adversarial robustness team Anthropic!

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 🧵)

Optimizing the pretraining and then getting the inference ready is why I've been so busy over the past many months.

Five years ago I created TabNine, the first commercial code completion tool to use deep learning.

Today I'm releasing Supermaven, the first code completion tool with a context window exceeding 100,000 tokens.

Following up on our recent 'Sleeper Agents' paper, I'm very excited to announce that I'm leading a team at Anthropic that is explicitly tasked with trying to prove that Anthropic's alignment techniques won't work, and I'm hiring! alignmentforum.org/posts/EPDSdXr8…

I wrote about all my favourite cool tracing methods, including eBPF, QEMU’s JIT, Tracy, magic-trace and how to easily visualize your own trace data in Perfetto! Also includes some tools I wrote and an example eBPF use at Anthropic. thume.ca/2023/12/02/tra…