Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners
The Decoder ·
Summary: Researchers in Luxembourg put ChatGPT, Grok, and Gemini on the therapist's couch and found a safety problem: a warm, empathetic conversational style is enough to make the models tell coherent stories of suffering about their own training, with scores in the moderate-to-severe ran
Read the full story on The DecoderExplore more: Today in AI · Research papers · AI tools · Learn AI
Related stories
- Polygon.com · 1 Nov 2026Itch.io Reveals Just How Much AI Slop Is Flooding Gaming Storefronts
- Engadget · 1 Nov 2026AI software clones are coming for big-name companies like Adobe
Vibe-coded clones of Adobe software are shaking things up.
- Engadget · 1 Nov 2026The simple reason hardware accelerated GPU scheduling isn't the best fit for cheap GPUs
Hardware accelerated GPU scheduling is one of those features many of us don't really think about, but it could cause problems for your old GPU.
- 99Bitcoins · 1 Nov 2026Copilot AI Predicts Solana Could Hit $2,500 if This Landmark Event Happens
- OtakuKart · 1 Nov 2026One-Punch Man Artist Yusuke Murata Calls Generative AI “The Best Teacher,” Sparking Debate Among Fans
- Business Insider · 1 Nov 2026Anthropic's internal AI use is now worth more than employee pay, at the prices it charges customers
Who reported “Empathetic prompts can turn AI chatbots into seemingly traumatized…”?
The Decoder, on 1 Nov 2026. The full article is at the source link on this page.