RSS

Dmitry Vaintrob

Karma: 1,929

Against blan­ket ar­gu­ments against interpretability

Dmitry VaintrobJan 22, 2025, 9:46 AM
50 points
4 comments7 min readLW link

Log­its, log-odds, and loss for par­allel circuits

Dmitry VaintrobJan 20, 2025, 9:56 AM
57 points
4 comments11 min readLW link

Is the­ory good or bad for AI safety?

Dmitry VaintrobJan 19, 2025, 10:32 AM
26 points
1 comment5 min readLW link

Renor­mal­iza­tion Re­dux: QFT Tech­niques for AI Interpretability

Jan 18, 2025, 3:54 AM
44 points
12 comments7 min readLW link

The quan­tum red pill or: They lied to you, we live in the (den­sity) matrix

Dmitry VaintrobJan 17, 2025, 1:58 PM
37 points
34 comments12 min readLW link

Per­ma­nents: much more than you wanted to know

Dmitry VaintrobJan 16, 2025, 8:04 AM
17 points
2 comments15 min readLW link