Hacker News Reader

The problem is that LLMs are basically roleplay simulators.

Re Karpathy: GPTs don't want to succeed. They want to imitate. https://twitter.com/karpathy/status/1627366416457555969?s=20

View on HN

Yes, I think we are going to need a new architecture for LLMs to move beyond, "that is interesting", to something that is reliable and can be used for trusted applications.

It's not an architecture problem of the transformer at all. This is the result of thinking the idea that you can make inviolable rules for a system you don't understand is not anything but ridiculous. You're never going to make inviolable rules for a neural network because we don't understand what is going on on the inside.

Reply on news.ycombinator.com