RSS

gekaklam

Karma: 137

Search­ing for a model’s con­cepts by their shape – a the­o­ret­i­cal framework

23 Feb 2023 20:14 UTC
50 points
0 comments19 min readLW link

[RFC] Pos­si­ble ways to ex­pand on “Dis­cov­er­ing La­tent Knowl­edge in Lan­guage Models Without Su­per­vi­sion”.

25 Jan 2023 19:03 UTC
47 points
6 comments12 min readLW link

First LessWrong Geneva Meetup

gekaklam8 Mar 2019 20:08 UTC
3 points
0 comments1 min readLW link