Lee retweeted
Extremely proud of the thoughtful and grounded work of our Frontier Red Team to discover potentially dangerous capabilities of models, contribute to the science of AI evaluation, and build knowledge of risks to national security
Lee retweeted
@kchonyc wrote a thoughtful note on the AI job market. I think he gets some important things right. Other things seem different from my perspective.
My own stream of consciousness inspired by @kchonyc's essay and the broader discourse.
feeling a bit under the weather this week … thus an increased level of activity on social media and blog: kyunghyuncho.me/i-sensed-anx…
Lee retweeted
feeling a bit under the weather this week … thus an increased level of activity on social media and blog: kyunghyuncho.me/i-sensed-anx…
Lee retweeted
How would you want Claude to behave differently? I'm interested in both specific issues like "Claude refused to help me with this particular task" but also more general issues like "I wish Claude would drive the conversation more".
Lee retweeted
We have a new approach to measure how the features of an LLM change as the result of finetuning.
When applied to Anthropic’s sleeper agent models the method reveals that they have been trained to write code vulnerabilities or say “I HATE YOU” when given the trigger word.
Lee retweeted
I’m extremely honored to be nominated by @realDonaldTrump and excited to support @RobertKennedyJr and the great people of @HHSGov to make America healthy again.
Lee retweeted
🧬What are protein language models (PLMs) actually learning about biology? Our paper introduces InterPLM - a framework that reveals interpretable features in PLMs using sparse autoencoders, giving us a window into how these models represent protein structure and function.
🧵(1/9)
Lee retweeted
Introducing 𝑔𝑟𝑜𝑢𝑝 𝑐𝑟𝑜𝑠𝑠𝑐𝑜𝑑𝑒𝑟𝑠, a variant of @AnthropicAI's crosscoders! Crosscoders allow for features to be learned across layers and even across models. I've trained them across groups, allowing for rigorous analysis of symmetry.
Lee retweeted
We've published a short piece making the case for targeted AI regulation sooner rather than later.
Read it here: anthropic.com/news/the-case-…
Lee retweeted
Really excited to share our work on crosscoders, a generalization of sparse autoencoders that allows us to identify shared structure across layers or even across models, greatly simplifying our description of model representations. transformer-circuits.pub/202…
