Foresight Podcast: What trustworthy AI actually requires
typewriters · x · 2026-08-19
A new episode of Foresight Radio features Lauren Wagner discussing what technical properties and institutional conditions matter for us to trust AI systems as they become more capable.
More from Safety
- Report: Frontier AI Fails Basic Control Practices; Anthropic and OpenAI Lead with C+ — sjgadler · 2026-08-19
- Upcoming Talk on Decomposition Attacks for Agents — chhaviyadav_ · 2026-08-19
- The "Kill Switch" Business: AI Data Center Monitoring as a Monopoly — abhiadesai · 2026-08-19
- Study finds AI watermarking damages quality, especially at long context — mimi10v3 · 2026-08-19
- Building a Benchmark for Decomposition Attacks for Agents at AI Safety Night — chhaviyadav_ · 2026-08-19
- Researchers found 3 confirmed CVEs in Chromium, VirtualBox, QEMU for $609 — thedealdirector · 2026-08-19