I've been waiting for someone to say this. An agent will generally produce far more code than technically necessary for the task. It's a kind of over engineering which makes it increasingly harder to wrap your head around the codebase.
The issue is provenance. We need cameras and phones to digitally sign photos so we can easily verify an unadulterated image.
You also want to be able chain signing so that for example a news reporter could take a photo, then the news outlet could attest its authenticity by adding their signature on top.
Same principle could be applied to video and text.
Signing something doesn't verify that it's real, it just verifies that you claimed that it was real, which everyone was already aware of. You can either hack a camera, or use an unhacked camera to take a picture of a fake picture.
Furthermore, if you simply try to push certain safety topics, you can see how actually can reduce hallucinations or at least make certain topics a hard line. They simply don't because agreeing with your pie-in-the-sky plans and giving you vague directions encourages users to engage and use the chatbot.
If people got discouraged with answers like "it would take at least a decade of expertise..." or other realistic answers they wouldn't waste time fantasizing plans.
> Related, where they're drinking coffee from a disposable cup, you can almost always tell it's empty by how they handle it.
NCIS has a running gag about that. In the show they invariably drink... some mysterious caffeinated product, I don't know if I'd call it coffee, with a straw. It always makes a slurping sound like the cup is nearly empty. Even when just handed a fresh cup.
That show is often lampooned for the silly "two idiots one keyboard" scene, but I am convinced they are doing dumb stuff like that on purpose.
