Accelerating AI Alignment Research (Talk)

I gave a keynote talk on how we should be thinking about accelerating AI alignment (safety) research. This is a topic I've been thinking about for a while and have given similar talks in the past, but I gave this one to kick off the hackathon I've co-organized with Apart Research this weekend.

If you'd like to learn more about how I've been thinking about this, here's the talk:

If you'd like to collaborate on this kind of work, let me know!

Here are the slides for the talk. Here's some related notes and project suggestions.

Sign up for Aligned to Flourish

Aligning AI and Flourishing

Subscribe .nc-loop-dots-4-24-icon-o{--animation-duration:0.8s} .nc-loop-dots-4-24-icon-o *{opacity:.4;transform:scale(.75);animation:nc-loop-dots-4-anim var(--animation-duration) infinite} .nc-loop-dots-4-24-icon-o :nth-child(1){transform-origin:4px 12px;animation-delay:-.3s;animation-delay:calc(var(--animation-duration)/-2.666)} .nc-loop-dots-4-24-icon-o :nth-child(2){transform-origin:12px 12px;animation-delay:-.15s;animation-delay:calc(var(--animation-duration)/-5.333)} .nc-loop-dots-4-24-icon-o :nth-child(3){transform-origin:20px 12px} @keyframes nc-loop-dots-4-anim{0%,100%{opacity:.4;transform:scale(.75)}50%{opacity:1;transform:scale(1)}}

Email sent! Check your inbox to complete your signup.

Consider subscribing to my newsletter to get notified when I release a new post!