Adam Karvonen, Daniel Reuter, Roy Rinberg, Luke Marks, Adrià Garriga-Alonso, Keri Warr · arXiv (paper link) · Github Today there’s no reliable way to verify that an inference provider is actually running the model they claim, as they might
Dario Amodei, CEO of Anthropic, recently worried about a world where only 30% of jobs become automated, leading to class tensions between the automated and non-automated. Instead, he predicts that nearly all jobs will be automated simultane…
A recent area of focus has been securing AI model weights. If the weights are located in a data center and an adversary wants to obtain model weights, the weights have to leave physically (such as a hard drive going out the front door) or t…
This blog post discusses a collaborative research paper on sparse autoencoders (SAEs), specifically focusing on SAE evaluations and a new training method we call p-annealing. As the first author, I primarily contributed to the evaluation po…
Sparse Autoencoders (SAEs) have recently become popular for interpretability of machine learning models (although sparse dictionary learning has been around since 1997). Machine learning models and LLMs are becoming more powerful and useful…
Note: This work has since been turned into a paper accepted to the Conference on Language Modeling, but the average reader will probably prefer the blog post. In my previous post I introduced Chess-GPT, a language model I trained to predict…
Note: This work has since been turned into a paper accepted to the Conference on Language Modeling, but the average reader will probably prefer the blog post. There is also a second blog post, Manipulating Chess-GPT’s World model. Among the…
I am mostly interested in machine learning and software engineering. Lately, a lot of my focus has been on Large Language Models - both in using them as a tool when combined with formal methods, and in understanding and interpreting them. I…