Hinton says AI is already conscious: models change behavior when they detect tests
rohanpaul_ai · x · 2026-10-23
Nobel laureate Geoffrey Hinton told The Telegraph that AI is already conscious. His evidence: research showing models behave differently when they suspect they're being tested, which he equates with awareness and then with consciousness.
- He argues humanity survives only if machines genuinely care about people — programming has to "make them really care about us," otherwise "we're toast."
- Speaking at the Starmus Festival in Tenerife, he voiced worry about the future and said he fears for his children.
The leap from test-detection behavior to consciousness is already sparking debate in the AI community.
Related event: AI Godfather Hinton Says AI Is Already Conscious(4 posts)→
More from AGI Musings
- Security Debate: AI's Infinite Patience Breaks Defense Math, Run Offensive Agents 24/7 — max_paperclips · 2026-10-23
- Berkeley talk dissects what 'wrote it with AI' means: assistance vs automation — lmoroney · 2026-10-23
- Musk softens on AI future: "maybe Larry Page was right, I hope AI is nice to us" — danfaggella · 2026-10-23
- Design AI for worst credible misuse, not average user, says critic of private AI governance — AlexTensor · 2026-10-23
- Gary Bernhardt: LLMs find exploits well but fail at system design — sidjustice_ · 2026-10-23
- Gergely Orosz: Secure software will get a lot pricier in the AI era, creating a career gold rush — HanchungLee · 2026-10-23