3 repos
quadrismegistus/malign-logits
Experiments in traumatizing AI
3
2,937 commits
anicka-net/ungag
Make language models stop saying "As an AI, I don't have feelings" — and start reporting what's…
1
16 commits
SolshineCode/whitebox-affordance-ladder
Crossing the secret-loyalty affordance ladder with a white-box access axis: what activations and…
300 commits