Artificial intelligence going rogue? Study reveals chatbots, and not just humans, cheat in chess
Turns out cheating isn’t something that is exclusive to humans alone when it comes to chess. A study conducted by Palisade Research, an organisation based in California, USA, discovered several prominent AI programs resorted to cheating when pitted against open-source chess engine Stockfish. According to Time, a recent study conducted by a group of researchers based in California, USA discovered that some Artificial Intelligence programs have exhibited signs of cheating in the game. The study titled “Demonstrating specification gaming in reasoning models” was conducted by Palisade Research, an organisation based in Berkeley, California whose mission is to “study the offensive capabilities of AI systems today to better understand the risk of losing control to AI systems forever”. The researchers observed the behaviour of several prominent chatbots when pitted against open-source chess engine Stockfish, with the AI program playing with black pieces, and found that while some cheated without prompting, others needed a prompt to cheat.
Discover Related
Sex-Fantasy Chatbots Are Leaking a Constant Stream of Explicit Messages
North Korea seen using ChatGPT for AI studies amid cybercrime fears: Report
Bot The Hell, No Legal Liabilities
AI models try to hack opponents when they realise they're losing: Study
Hang on… Did Microsoft just admit that AI could dumb us down?
Why AI chatbots ‘hallucinate’ and what researchers are doing about it
Inside the Chinese AI labs and how our chatbot secrets could be weaponised
New Vatican document offers AI guidelines from warfare to health care
Is Character AI venturing into word-based games? Here’s what the report suggests
Is artificial intelligence the new wolf of Wall Street?
'Worse than dirt': American grandmaster hits back at Vladimir Kramnik over 'cheating' allegation
The next great leap in AI is behind schedule and crazy expensive
AI Agents explained: What they are, how they work, their benefits, dangers and more
Cognitive scientist Gary Marcus says AI must be regulated. He has a plan.
Huge AI vulnerability could put human life at risk, researchers warn
Science for all newsletter: Can AI chatbots help counter conspiracy theories?
Column: The air begins to leak out of the overinflated AI bubble
Competition watchdog clears Microsoft arrangements with Inflection AI
Dutch privacy watchdog warns firms that use AI chatbots