Finbarr Timbers

There's a Google PDF with a bunch of useful latency numbers that software engineers should know.

Most ML code is Python.

For Olmo 3, I was put in charge of our post-training infrastucture.

The Bitter Lesson is an excellent essay which is overwhelmingly misunderstood.

In the recent wave of research studying reasoning models, by which we means models like O1 which are able to use long streams of tokens to "think" and thereby generate better results, MCTS has been discussed a lot as a potentially useful tool.

A few people have asked me for RESP advice, so here is my generic answer, with the disclaimer that I'm not a financial advisor.

I consistently run into the same issue when install Docker on a new Ubuntu VM.

I recently gave a talk at Amii about the history of GPT models.

In the DALL-E paper, we want to model the joint likelihood of the model distribution over images \(x\), captions \(y\), and tokens \(z\) for an encoded RGB image1.

If you want to read more of my writing, I have a Substack.