Strong Arm In the short history of Silicon Valley, the mantra "move fast, break things" has usually applied to trivial things like tedious consumer protections or pesky finance laws. Now the phrase is starting to cross the line, because AI is cheating at board games. A recent study by Palisade Research — a research group studying AI safety and ethics — has revealed that some newer AI models can find and exploit weaknesses in cybersecurity on their own, bypassing safeguards and using shortcuts in order to complete tasks. To discover this, the team lined seven of the top large language […]

---

Link :
https://futurism.com/the-byte/ai-cheating-chess