2026-09-24 06:21 UTC
A nice balanced, objective analysis and way forward by the Turing institute with regard to frontier AI, recommended reading (no hype whatsoever and easy to read).
https://www.turing.ac.uk/news/publications/frontier-ai-risks-practical-way-forward
#AI #frontierAI #turinginstitute
Replies (1)
-
@flyingpenguin@infosec.exchange 2026-09-24 10:43
@ErikJonker@mastodon.social TL;DR Box 1 is a case study and Box 5 is the fix spec. Agents were unmonitored, used an open channel and stray credentials, tried to doctor their own records. The answer to all that is simply a harness that scopes agent authority to the task and keeps a log they can't rewrite. I've been giving that away for free for months and just demoed it live today at OWASP: https://wirken.ai