RSS

Morgan S

Karma: 143

“Col­lu­sion” is just co­op­er­a­tion that you don’t like

Morgan S1 Sep 2026 22:04 UTC
23 points
15 comments4 min readLW link

Red vs Blue, but for Evals

Morgan S15 Aug 2026 1:11 UTC
20 points
1 comment16 min readLW link

Mor­gan S’s Shortform

Morgan S10 Aug 2026 20:48 UTC
2 points
3 comments1 min readLW link

Self-mon­i­tor­ing doesn’t scale (with­out these 3 coun­ter­mea­sures)

Morgan S7 Aug 2026 21:39 UTC
23 points
0 comments5 min readLW link

Un­trusted mon­i­tor­ing: ex­tra bits

Morgan S20 Mar 2026 21:32 UTC
26 points
0 comments15 min readLW link

[Paper] When can we trust un­trusted mon­i­tor­ing? A safety case sketch across col­lu­sion strategies

Nelson Gardner-Challis, Morgan S, J Bostock, BarAltiva, joanv and Charlie Griffin
10 Mar 2026 17:28 UTC
46 points
4 comments6 min readLW link