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.
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.
If too much of these services are provided by another country, that country could severely cripple your infrastructure by denying you service. In times of international conflicts, this could be a very serious problem.
Im convinced i just post rationalize my instinctive behaviour. But my instincts react not only to the external world, but also to my previous thoughts. So my reasonings influence somewhat my behaviour, they dont dictate my behaviour, but they influence it.
Polluting is a bit different from taking resources. The industry should be more regulated, which would maybe convert the damage made to the environment into an increased price of beef.
Ikr, public transportation just gets worse and worse around here. Metro barely covers 10% of the city and is expensive, buses are incredibly unreliable. I still manage to get around without a car, but its so frustrating.
If i got it right, flatpacks gather all of the dependencies of the package and bundles them with tha package. Maybe those extra 290mb were from dependencies that you already had installed but that flatpak wanted to install another copy.
Nice mental gymnastics, but if 5 is so good, how come five five's is so bad?
Who cares about the pentagon? The broad use of 5 everywhere just shows how its a banal number, how worthless it is. Now 25 is reserved for much greater things, any toddler knows it shouldnt be overused.
I think pirating scientific papers is a good thing all around. The research isnt funded by the selling of access to those papers, much on the contrary.
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.