Cross-posts
Collaborative posts I've co-authored, originally published on LessWrong and mirrored here in full — for preservation, and so they live in the repo rather than only behind a link that might one day rot. Original authorship and order are preserved; each links back to the canonical LessWrong version.
2025-12-17
crosspost
Shallow review of technical AI safety, 2025
technicalities, Tomáš Gavenčiak, Stephen McAleese, peligrietzer, Stag, jordinne, ozziegooen, Violet Hour, lenz · on LessWrong ↗
2025-08-28
crosspost
Here’s 18 Applications of Deception Probes
Cleo Nardo, Avi Parrack, jordinne · on LessWrong ↗
2025-04-15
crosspost
Can SAE steering reveal sandbagging?
jordinne, Hoang Khiem, Felix Hofstätter, Cleo Nardo · on LessWrong ↗
2024-12-29
crosspost
Shallow review of technical AI safety, 2024
technicalities, Stag, Stephen McAleese, jordinne, Dr. David Mathers · on LessWrong ↗
2024-06-14
crosspost
Results from the AI x Democracy Research Sprint
Esben Kran, jordinne, Jason Hoelscher-Obermaier · on LessWrong ↗