Hamish Ivison

The self-play paradigm is self-evidently self-exciting.

These are a lightly adapted set of notes for a ‘RL101’ lecture I gave for some research groups meetings.

Note to reader: This blog post is a (lightly) edited version of a post I originally wrote in May 2025, but dropped due to getting busy with life.

As usual, I’m sharing what media I watched, read, played, and so on in 2025.

I keep track of everything I read, play, and watch over the year, and looking back is always fun.

I’ve kept track of most media I watch, read, or play for the past few years.

Note: This post is very much my own personal experience.

I don’t know quite why, but recently I’ve been thinking about zero-shot multilingual translation, and so I decided to try to see how well GPT-3 can handle low-resource ancient languages.

As a quick note, I’ve recently done a go-over of the design of my blog.

tl;dr: check out a fun little Ace Attorney generator I made!