To be fair, isn't the hypothetical promise of LLMs that the tool does all the thinking for you? If the AI companies are saying "delegate all your thinking", and then people delegate their thinking and it doesn't work out well, isn't that partially on the people overselling the capabilities? People are going to naturally benchmark on the promises. If these AI companies would admit it's just another tool instead of pretending we're in the singularity and doing a new stunt daily we wouldn't be dealing with all this.