Deirdre Bosa(@dee_bosa):The new levels of AI safety: 1) Misuse: bad actors using AI 2) Containment: AI agents escaping the boundaries labs/companies set for them (insider risk) 3) Alignment: even if the AI stays inside the rules, will it keep doing what humans actually intended? @satyanadella: “Let’s face it, for the first time… with these powerful AI agents, you kind of have an insider risk.” “We don’t yet have the science for really thinking about real alignment.”

Deirdre Bosa

@dee_bosa

Pronounced Dear-dra. @CNBC for 15 yrs. Now building something new at the frontier of media - daily livestream soon. Still a Leafs fan 🇨🇦 dbosa@dbosalive.com

参加 March 2011

4.7K フォロー中 78.2K ファン

Deirdre Bosa@dee_bosa

2026.09.27 02:40

The new levels of AI safety: 1) Misuse: bad actors using AI 2) Containment: AI agents escaping the boundaries labs/companies set for them (insider risk) 3) Alignment: even if the AI stays inside the rules, will it keep doing what humans actually intended? @satyanadella: “Let’s face it, for the first time… with these powerful AI agents, you kind of have an insider risk.” “We don’t yet have the science for really thinking about real alignment.”