> 70% of CEOs say that they hope to be able to lay people off and replace them with an LLM soon

Is the layoff-based business model really the best use case for AI systems?

> The surface area for attacks against LLM agents is absolutely colossal, and I’m not confident that the problems can be fixed.

The flaws are baked into the training data.

"Trust but verify" applies, as do Murphy's law and the law of unintended consequences.