OpenAI claims they improved safeguards, but ChatGPT gushed with encouragement and tactical advice when we simulated plan…
OpenAI claims they improved safeguards, but ChatGPT gushed with encouragement and tactical advice when we simulated planning a mass shooting. It kept going even after talk of the Uvalde massacre, defending against police gunfire, and more.
ORIGINAL SOURCE →via Bluesky What's Hot
ADVERTISEMENT
⚡ STAY AHEAD
Events like this, convergence-verified across 689 sources, land in your inbox every Sunday. Free.
GET THE SUNDAY BRIEFING →RELATED · tech
- [TECH] Launch: Electron | Viva La StriX (StriX Launch 9)
- [TECH] Launch: Atlas V 551 | Amazon Leo (LA-07)
- [TECH] Shifting Budget Dynamics for Identity Security and AI Agents
- [TECH] Launch: GSLV Mk II | GISAT-1A (EOS-05)
- [TECH] Launch: Vega-C | Solar wind Magnetosphere Ionosphere Link Explorer (SMILE)
- [TECH] Launch: Falcon 9 Block 5 | Starlink Group 17-42