RSS

Jannes Elstner

Karma: 109

Researching scheming at Apollo Research

Con­sis­tency Train­ing while Miti­gat­ing Obfus­ca­tion via Rate Matching

Sohaib Imran, Prakhar Gupta, Jannes Elstner and David Africa
1 Jul 2026 17:26 UTC
50 points
7 comments12 min readLW link

Im­prov­ing Petri schem­ing au­dits with en­vi­ron­ment blueprints

Jannes Elstner26 May 2026 0:31 UTC
13 points
0 comments6 min readLW link

Un­der­stand­ing when and why agents scheme

Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad, David Lindner and LASR Labs
21 Mar 2026 20:33 UTC
50 points
2 comments4 min readLW link

Cur­rent LLM agents need strong pres­sure to en­gage in schem­ing behavior

Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad, David Lindner and LASR Labs
20 Nov 2025 20:45 UTC
24 points
1 comment11 min readLW link