AI ALIGNMENT FORUM
AF

Violet Hour

Message

https://theviolethour.substack.com/

240

Shallow review of technical AI safety, 2025

Website version · Gestalt · Repo and data Change in 18 latent capabilities between GPT-3 and o1, from Zhou et al (2025) This is the third annual review of what’s going on in technical AI safety. You could stop reading here and instead explore the data on the shallow review...

Dec 17, 2025•178

Violet Hour

https://theviolethour.substack.com/

Violet Hour — AI Alignment Forum

Violet Hour

Message

https://theviolethour.substack.com/

240

Shallow review of technical AI safety, 2025

Dec 17, 2025•178

Violet Hour

https://theviolethour.substack.com/

Shallow review of technical AI safety, 2025

technicalities

technicalities, Tomáš Gavenčiak, Stephen McAleese, peligrietzer, Stag, jordine, ozziegooen, Violet Hour, ramennaut+ 0 more

technicalities, Tomáš Gavenčiak, Stephen McAleese, peligrietzer, Stag, jordine, ozziegooen, Violet Hour, ramennaut

2mo

Website version · Gestalt · Repo and data

Change in 18 latent capabilities between GPT-3 and o1, from Zhou et al (2025)

This is the third annual review of what’s going on in technical AI safety. You could stop reading here and instead explore the data on the shallow review website.

It’s shallow in the sense that 1) we are not specialists in almost any of it and that 2) we only spent about two hours on each entry. Still, among other things, we processed every arXiv paper on alignment, all Alignment Forum posts, as well as a year’s worth of Twitter.

It is substantially a list of lists structuring 800 links. The point is to produce stylised... (read 24743 more words →)

•••