strategy tag
Closed weights.
Keep frontier weights closed; treat them as hazardous artefacts
People on the record.
2
Jeffrey Ladish
Executive Director of Palisade Research
Empirically demonstrates removing RLHF safety from open-weight models, arguing that releasing weights is irreversible proliferation.
Releasing the weights of a frontier model is a one-way operation. You cannot uninvent a weapon.
Lawrence Lessig
Harvard Law professor; Creative Commons founder
Long-time openness advocate who in 2024 argued the highest-capability AI models may need to be closed-weight despite his free-culture priors.
“Whatever model weights can teach, that benefit must be weighed against the enormous risk of misuse that highly capable models present. At some point, that risk is clearly too great.”