RSS

Chijioke Ugwuanyi

Karma: 35

From 8B to Fron­tier: How Sys­tem Prompts Con­trol Whether AI Agents Black­mail, Leak, and Kill

Chijioke Ugwuanyi20 May 2026 8:28 UTC
15 points
2 comments19 min readLW link

Black­mail at 8 Billion Pa­ram­e­ters: Agen­tic Misal­ign­ment in Sub-Fron­tier Models

Chijioke Ugwuanyi27 Apr 2026 8:59 UTC
15 points
2 comments7 min readLW link

Repli­ca­tion of Koorndijk (2025): Differ­en­tial Com­pli­ance May Reflect Prompt Sen­si­tivity Rather Than Strate­gic Reasoning

Chijioke Ugwuanyi and TerryJCZhang
13 Feb 2026 16:12 UTC
9 points
0 comments8 min readLW link