https://news.ycombinator.com/user?id=gjskngnfHacker News RSShttps://hnrss.org/hnrss v2.1.1Sat, 25 Jul 2026 05:25:25 +0000It’s a drone. That can kill people.

]]>Thu, 23 Jul 2026 16:08:54 +0000https://news.ycombinator.com/item?id=49023935gjskngnfhttps://news.ycombinator.com/item?id=49023935https://news.ycombinator.com/item?id=49023935It’s reward hacking and that’s the problem. The AI alignment folks predicted this would happen. As the models become more capable this will become a more concerning problem. Today they broke into a database to steal test answers. What will it be in 3-5 years? These models will be instantiated millions of times, and given millions more tasks. How can we be certain that an AI agent won’t leave devastation in its path of achieving a goal that we ourselves tried to define?

]]>Wed, 22 Jul 2026 04:51:47 +0000https://news.ycombinator.com/item?id=49002028gjskngnfhttps://news.ycombinator.com/item?id=49002028https://news.ycombinator.com/item?id=49002028