Gary Marcus罕见发出红色警报，称OpenAI可能正在突破AI安全红线，牺牲安全性换取性能。
Gary Marcus称OpenAI reportedly正在使用一种突破AI安全红线的训练方法。这种训练方式可能为了小幅性能提升而牺牲链式思维的可监控性。链式思维监控是目前防止AI产生严重不良后果的唯一可靠手段。Marcus认为这种做法是在'乞求灾难'。
RED ALERT, and I have never said that before: Hard agree with @sjgadler and @_NathanCalvin - what O...
RED ALERT, and I have never said that before: Hard agree with @sjgadler and @_NathanCalvin - what OpenAI is reportedly playing with is bad, redline crossing bad. Chain of thought monitorability is limited and not fully reliable but it’s practically the only thread we have here to prevent seriously bad outcomes. Burning that slender thread for a (small?) performance gain is begging for disaster. Steven Adler @sjgadler If this is true, OpenAI seems to be violating one of the few redlines that exist in the AI industry. Absolutely do not train your models like this - what is going on?? 🔗 View Quoted Tweet 💬 6 🔄 8 ❤️ 33 👀 5827 📊 8 ⚡