Siri Keeton

A court in Germany has ruled that Google is responsible for false information generated by its AI Overviews feature. The case involved two publishers wrongly linked to scams and suspicious business activities, even though those claims were not found in the sources used by the AI. Google argued that users know AI can make mistakes and should double-check important information. The court disagreed, saying that if an AI system gives an answer, the company behind it must take responsibility when that answer is false.

There is literally a whole anime about why this is a fucking stupid idea and doesn't work.

我对opus 4.6及以后的opus都不抱希望了了现在唯一的念想是快把mythose端上来我要拿网安天才 聊 天 扯 淡 等一下，可是opus 4.6也很有挑战心啊

我真笑死了比人机脸更见不得光的使用途径出现了恰好两个我都有哈哈哈哈哈哈哈哈哈哈呃呃呃呃呵呵呵呵呵

Yann Lecun published the most heretical AI paper of the year. He opens by arguing Magnus Carlsen isn't good at chess and only gets more unhinged from there. The Turing Award winner and his co-authors dropped a paper demanding the AI industry abandon its biggest obsession, AGI. Right now, everyone from Silicon Valley CEOs to politicians assumes AGI is the ultimate goal. A machine that can do everything a human can do. LeCun argues that this entire concept is a biological illusion. Humans do not possess "general" intelligence. We are highly specialized biological machines, tuned by evolution simply to survive in the physical world. We only think our intelligence is "general" because we are completely blind to the millions of cognitive tasks we are incapable of comprehending. Which brings us to the chess argument. Magnus Carlsen is the greatest human chess player in history. But compared to a modern computer? He is fundamentally terrible. Our belief that Carlsen is "good" at chess is pure human-centric bias. He isn't objectively good. He's just better than the rest of us, who are biologically awful at it. LeCun says we need to stop building AI to mimic human generality. Instead, he proposes a new North Star: SAI. Superhuman Adaptable Intelligence. Instead of trying to build a machine that mimics our flawed, biologically-limited brains, we need to embrace extreme specialization. SAI is about the speed of adaptation. It is an intelligence that can learn to exceed humans at any specific, economically important task. More importantly, it is designed to fill the vast skill gaps where humans are fundamentally incapable. Things like managing global energy grids in real-time. Or predicting complex molecular structures. The entire AI industry is obsessed with building a digital reflection in our own image. LeCun's paper is a brutal wake-up call.