By default powerful ML systems will have dangerous capabilities (such as hacking) and may not do what their operators want. Frontier AI labs should design and modify their systems to be less dangerous and more controllable. In particular, labs should:| ailabwatch.org
Without great security, sophisticated actors can steal AI model weights. Thieves are likely to deploy dangerous models incautiously; none of a lab’s deployment-safety matters if another actor deploys the models without those measures.| ailabwatch.org
Labs should:| ailabwatch.org
When a dangerous model is deployed, it will pose misalignment and misuse risks. Even before dangerous models exist, deploying models on dangerous paths can accelerate and diffuse progress toward dangerous models.| ailabwatch.org
How are AI companies doing with their voluntary commitments on vulnerability reporting?| adamjones.me