Zero :zt_think: :artix: on Nostr: [RT]( ) [@Jonathan_Blow@x.com]( ): When operating LLMs in a conversational mode, it's ...

[RT](https://x.com/Jonathan_Blow/status/2089539369715851746 ) [@Jonathan_Blow@x.com](https://x.com/Jonathan_Blow ): When operating LLMs in a conversational mode, it's clear that they are deeply subject to suggestion, and spend a lot of energy just following the implications built into the questions you ask.

"Estimate this quantity." It does so, gives you a long explanation, and it seems convincing.

"Wait, don't you think this number should be higher, because of reason X?" It will say yes of course, I didn't properly consider X, here is a higher answer.

"Wait, don't you think this number should be lower, because of reason Y?" Yes of course. It will give you a lower answer.

People use these for programming.