RSS

Andrey Anurin

Karma: 9

Nat­u­ral Lan­guage Au­toen­coders are sum­ma­riz­ers, but do they have to be?

Andrey Anurin9 Jul 2026 19:54 UTC
8 points
1 comment22 min readLW link

Catas­trophic Cy­ber Ca­pa­bil­ities Bench­mark (3CB): Ro­bustly Eval­u­at­ing LLM Agent Cy­ber Offense Capabilities

Jonathan N, Andrey Anurin, Connor Axiotes and Esben Kran
5 Nov 2024 1:01 UTC
9 points
0 comments6 min readLW link
(www.apartresearch.com)