NLProject Tailwind: AI Security & Verification
Coefficient GivingRemote
Why this is on the board
International agreements on powerful AI are only worth something if countries can check whether the other side is keeping to them, and the technology for that checking largely does not exist yet. With the budget of a large funder like Coefficient Giving (formerly Open Philanthropy), you set up the hardware, protocols and teams that others build on, and so help decide which agreements can be verified later on.
This board is in beta and this is our judgement. If you think we have it wrong, tell us. Give feedback · How we reason about it
About the role
Launch ambitious R&D and capacity-building initiatives to develop AI security verification technology, strengthen talent pipelines between cybersecurity and AI sectors, and establish integrity standards against backdoor attacks. - Design and build tamper-resistant hardware and end-to-end verification protocols for international AI development agreements. - Develop security protocols and auditing standards to detect and prevent AI integrity attacks and backdoors. - Build talent pipelines and i…
Want to understand this first?
Start with our free course: about 100 minutes in six short units, at your own pace, with no sign-up. To go further, apply for the EA Fellowship: five weeks of reading and discussion in a small group. Also free, but selective.