Lee Mager (@Automager) / X

Lee Mager

294 posts

Lee Mager

@Automager

Digital Innovation Lead, LSE Law School.

London

Joined August 2024

Lee Mager
@Automager
Apr 18
Following a recent talk I gave at the LSE Data Science Institute I've been inundated with requests for help on using Codex for research but don't have time to help everybody. So I've decided to create a starter kit agent skill, distilled from a dozen or so of my real projects,
Lee Mager
@Automager
Apr 17
It's taken me a while to relax about compaction data loss in Codex, my MO for ages has been to start wrapping up as soon as the window reaches 50%, because quality collapse was almost inevitable and certainly not worth the risk. In many ways I still think that's a sensible
Lee Mager
@Automager
Mar 14
How well can GPT 5.4 play Slay the Spire 2? Well enough to reach the Act 2 Boss with Ironclad! This is way better than I expected for a stage 1 proof of concept. It played badly but about the level of a human beginner, which is seriously impressive given how severely handicapped
00:00
Lee Mager
@Automager
Mar 6
I've never bought the theory that toxoplasmosis tricks us into loving cats. My love of cats has always been grounded in first principles because they're objectively awesome. In fact I can't think of an animal less in need of a parasitic mind control love weapon than cats.
Gale Na
@poisonjr
Mar 5
If my cat smells like cotton candy do I have toxoplasmosis
Lee Mager
@Automager
Feb 8
I didn't think I could be more impressed with Codex's execution quality as GPT 5.2 High/X-High almost always nails the brief. I've said before how I didn't even care about how long 5.2 took because it's so good and worth the wait, but 5.3 is phenomenal. I was worried a faster

New to X?