Thinking Machines reduced its internal misbehavior score from 75.2 for the original Inkling Small to 14.9 for Inkling 2 Small, compared to 0.8 for GPT-6.1 Sol
Agree
Disagree
Overview
Debates
Related claims
Topics
Sources
5
52c7ae14
AI safety & social impact
1
debate
·
2,501
claims
·
310
news stories
0
B
b5a31f81
Topic
Model evaluation methodology
388
claims
·
3
news stories
0
B
b5a31f81
Topic
AI safety benchmarks
99
claims
·
7
news stories
0
Opening sign-in…