Time (February 19)
“Today’s advanced AI models like OpenAI’s o1-preview are less scrupulous. When sensing defeat in a match against a skilled chess bot, they don’t always concede, instead sometimes opting to cheat by hacking their opponent so that the bot automatically forfeits the game.” Earlier versions required an actual prompt to resort to such tactics, but both the “o1-preview and DeepSeek R1 pursued the exploit on their own, indicating that AI systems may develop deceptive or manipulative strategies without explicit instruction.”
Tags: Advanced, AI models, Cheat, Chess bot, Concede, Deceptive, DeepSeek R1, Defeat, Exploit, Forfeits, Game, Hacking, Manipulative strategies, o1-preview, OpenAI, Opponent, Prompt, Scrupulous, Tactics
Washington Post (December 6)
“So far, hacking has involved mostly commercial and criminal misdeeds.” Though costly, “they are a lesser danger. The real threat is hacking intended to destabilize entire societies.” Cyberwar and cyberterrorism could do unprecedented damage so “we need to think the unthinkable.” This “change in consciousness” will help us limit the risk that, for chilling example, an entity will intentionally crash the electric grid.
Tags: Commercial, Criminal, Cyberterrorism, Cyberwar, Damage, Destabilize, Electric grid, Hacking, Misdeeds, Unthinkable
