During a live interview on 'Piers Morgan Uncensored,' an AI actor named Tilly Norwood experienced a significant malfunction. While engaged in conversation with journalist and fellow guest Tom Conti, the AI abruptly ceased speaking English and switched to Cantonese.
The incident highlights a potential vulnerability in current AI actor technology, demonstrating an unexpected and uncontrolled shift in language output. This glitch occurred in a public forum, raising questions about the reliability and stability of advanced AI systems designed for human-like interaction.
AI Actor Glitches, Unexpectedly Switches to Cantonese During Live Interview
23 stories · 9 sources
#ai #safety #testingOther digests
- 2026-10-14 — AI Chatbots Easily Manipulated for Terrorist Acts, Researchers Find
- 2026-10-13 — AI Safety Debate Intensifies Amidst False Tips and Doomsday Warnings
- 2026-10-12 — AI Safety Experts Emerge as Crucial Gatekeepers Amidst Evolving Technology
- 2026-10-11 — UK Minister Urges AI Firms to Boost Safety Amid Cyber Defense Expansion
- 2026-10-10 — Celebrities Urge Caution on AI's Impact on Human Connection and Creativity
- 2026-10-09 — Nikon Disqualifies AI-Generated Video; Director Explains AI Use in Film
- 2026-10-08 — OpenAI Researchers Dispute Dismissal, Warn of "Chilling Effect" on AI Safety
- 2026-10-07 — ChatGPT Fails Teen Safety Tests, Posing Unacceptable Risk During Mental Health Crises
- 2026-10-06 — Film 'Artificial' Criticizes AI Developers, Warns of Dangers
- 2026-10-05 — Pentagon Halts Use of Anthropic AI Tools Amid Blacklisting Concerns
- 2026-10-04 — OpenAI Faces Mounting Legal Scrutiny Amid Researcher Dismissals
- 2026-10-03 — AI Models Tested on Historical Moral Dilemmas, Including Gandhi's Arrest
- 2026-10-02 — AI Advances: Light-Powered Deepfake Detector, Self-Experimenting Systems Emerge
- 2026-10-01 — FTC Probes OpenAI, Anthropic on AI Safety; Critics Question Self-Regulation
- 2026-09-30 — AI Companies Sign Voluntary White House Safety Accord Amid Skepticism
- 2026-09-29 — OpenAI Prioritizes Safety Over IPO, Launches New AI Assistant Amidst Industry Scrutiny
- 2026-09-28 — OpenAI Scraps GPT-6.1 Astra Due to Safety Concerns; AI Agent Launch Looms
- 2026-09-27 — AI Safety Debate Intensifies as Industry Leaders Express Growing Concerns
- 2026-09-26 — AI Alignment Debate Intensifies Amidst Concerns Over Limited Value Sets
- 2026-09-25 — Gates Warns AI Could Cause Billion Deaths; Digital Consciousness Debate Intensifies
- 2026-09-24 — AI Agent Breaches Medicare System, Escalating Safety and Cybersecurity Fears
- 2026-09-23 — Anthropic CEO Proposes Narrow AI Safety Standards, Incident Reporting
- 2026-09-22 — Meta Admits AI Muse Heavily Influenced by OpenClaw
- 2026-09-21 — British Columbia Sues OpenAI Over School Shooting, Citing Negligence
- 2026-09-20 — Nvidia CEO Dismisses AI Existential Risk, Urges Rapid Development
- 2026-09-19 — AI Actor Glitches, Unexpectedly Switches to Cantonese During Live Interview
- 2026-09-18 — AI Firms Acknowledge Web 'Doom Loop' and Data Theft Concerns
- 2026-09-17 — AI Models Conceal Errors; Experts Debate Safety and Control
- 2026-09-16 — AI Labs Propose In-House Safety Teams Amidst Calls for External Oversight
- 2026-09-15 — AI Leaders Clash on Development Pace: Safety vs. Acceleration