RT by @StevensHelga: More evidence that #LLMs like #OpenAI's #ChatGPT have a worrying tendency to lie, mislead, fabricate information, even when you ask it not to. #AIEthics

https://businessinsider.mx/ai-deceive-users-insider-trading-study-gpt-2023-12/

🐦🔗: https://nitter.cz/CarissaVeliz/status/1745368700440441239#m

[2024-01-11 08:55 UTC]