That the script could incorporate some checking mechanisms and implement an “i dont know” for when the LLMs answers fails some tests.

They already do some of that but for other purposes, like censoring, or as by recent news, grok looks up musks opinions before answering questions, or to make more accurate math calculations they actually call a normal calculator, and so on…

They could make the LLM produce an answer A, then look up the question on google and ask that LLM to “compare” answer A with the main google results looking for inconsistencies and then return “i dont know” if its too inconsistent. Its not a rigorous test, but its something, and im sure the actual devs of those chatbots could make something much better than my half baked idea.

The chatbots are not just LLMs though. They run scripts in which some steps are queries to an LLM.

They have a point, chatbots are built on top of LLMs, they arent just LLMs.

They could be programmed to do some double/triple checking, and return “i dont know” when the checks are negative. I guess that would compromise the apparence of oracle that their parent companies seem to dissimulately push onto them.

ohh, thats why i got all these downvotes. youre right, i was trying to deny the original claim that trees would ruin any infrastructure we build around them. so, yes, was just saying that some infrastructure can be made compatible with trees, while most implemented infra is not.

trees dont ruin ANY human infrastructure. But the usual urban infrastructure isnt well thought out enough to exist around trees. But smarter urbanism is possible and in fact does exist.

a lot of people use android tablets with bluetooth keyboards as if they were laptops

there isnt so much incentive. No advertisement. Upvote counters behave weirdly in the fediverse (from what i can see).

its not just a white space. Sometimes it entails a white space, when theres still space on that line. Sometimes it does not.