Quick note on OpenAI and Erdős’s unit distance problem

Top-line reaction: It’s so incredibly important to see all of the actual details here to make an honest assessment of the result’s import. E.g., How many problems were they working on? In what areas? What prompts/inputs were used, and how many? What models with what settings? What was left out of the “abridged” (70k word, likely…

How we give feedback

Recently I’ve been thinking about giving feedback, partly spurred by Kino’s post. I’ve spent a lot of my time over the years thinking (and reading) about what feedback should do and should look like, as well as what it (typically) does do and does look like. This is for a lot of reasons: my own…