The craziest experiment in my lab is a new setup by @diatkinson.bsky.social where he has found a way induce introspection on open LMs using Dillon Plunkett's protocol, that lets him look inside introspection. It's nuts. Here's how the experiment works... 🧵 →

Ben Recht

beenwrekt.bsky.social

13 September 2026 00:37

Good thread by Colin here, refuting the weird rationalist ideas about AI and utility monsters (sadly held by people who now have far too much money and power).

Just discovered this very interesting blog post by @davidbau.bsky.social. davidbau.com/archives/202... It is an interesting formulation of the idea that it is up to humans to decide what world is worth building (and to take responsibility for the results)

You can play the contest too, at mazesofmenace.ai. Just point your coding agents at the repo github.com/davidbau/te... Nobody has cracked it yet: the field is wide open.

Is it possible to write 100,000 lines of code well, if you do not read it? Let's go Hunting Zombies! davidbau.com/archives/20... In this post I dive into the code of two AI agent contestants in the Teleport coding challenge to learn their secrets. Very fun. And also instructive.