Safety
What safety challenges do AI reasoning models present, and how can we address them? At TAIS 2026, we brought together four leading voices in…
What safety challenges do AI reasoning models present, and how can we address them? At TAIS 2026, we brought together four leading voices in AI safety to debate exactly that: Gary Marcus @GaryMarcus (
What safety challenges do AI reasoning models present, and how can we address them? At TAIS 2026, we brought together four leading voices in AI safety to debate exactly that: Gary Marcus @GaryMarcus (NYU), Victoria Krakovna @vkrakovna (Google DeepMind / Future of Life Institute), Andrei Krutikov @KrutikovAndrei (Noeon Research), and Fazl Barez @FazlBarez (University of Oxford), moderated by Blaine Rogers @blainewrogers (Noeon Research). The panel moves fast through some of the field's sharpest open questions: why reasoning matters for generalizing beyond training data, how scheming risks could change as models become better long-term planners, and a genuinely surprising finding — longer chains of thought can make models easier to jailbreak, not safer ("chain-of-thought hijacking"). They also push into whether today's safety research is too narrowly built around transformer LLMs, and what neurosymbolic systems, world models, and continual learning might demand instead. Watch the full panel on our YouTube channel: https://youtu.be/unqm-xV_E-8
Related
- @GaryMarcus, great interview and explanations of the challenges in AI. https://youtu.be/_pSivPlRx5o?is=dlFN6YBXsMA-tW4h
- None of the four of us believe that LLMs on their own are sufficient for AGI.
- The state of LLMs in one video #AI
- Gary Marcus @GaryMarcus (Emeritus Professor, New York University) took the stage at TAIS 2026 and made the case that, 'LLMs are not the way …
Source: Gary Marcus (X) | 2026-10-19