Debate: can AI agents be kept safe from hidden instructions on websites?
neil_chilson · x · 2026-11-10
Open to Debate hosted a discussion on whether AI agents can be kept safe from hackers.
- @meredith argues attackers can hide instructions on ordinary websites that trick an agent into causing harm, and even the best-funded AI labs haven't solved the problem
- @neilchilson counters that layered safeguards can keep the risk in check, much as we learned to manage computer viruses without eliminating them
The full debate video is available online.
More from coding & agent
- Hermes64 plugin turns any idea into an N64-style 3D game for Nous hackathon — Teknium · 2026-11-10
- Claude rebuilds Ocarina of Time's Kokiri Forest inside Valheim, zero code written — Any-Explanation3814 · 2026-11-10
- Cortex hits 73.2% on τ³-bench banking, 18 points above best published model — multiply_matrix · 2026-11-10
- Tailscale OAuth apps go GA, letting AI agents reach private MCP servers securely — rudrank · 2026-11-10
- Medium launches TK, a writing app that plugs your notes into AI agents via MCP — LuoSays · 2026-11-10
- Developer dedicates a Mac mini as a home for his AI agents — ow · 2026-11-10