The thing that AI is best at is summarizing vast quantities of information. That means the most natural thing for an AI to do is be "the one tool to rule them all".
The more information it has access to, the more useful the answer can be. But that also means that it can answer all the questions.
>> The thing that AI is best at is summarizing vast quantities of information
by definition a summary is the best at nothing though, and the mentality that the best way to rule is from a single summarized interpretation is both flawed and scary. It's not answering all questions; it's attempting to provide a single summation dramatically influenced by training. Go ahead and incorporate this into your balanced and multi-perspective decision-making process, but "one tool to rule them all" is not the same thing and definitely not what we're getting.
"If all you have is an LLM, every problem looks like summarizing information."
Emphasis on looks like ;-)
> the mentality that the best way to rule is from a single summarized interpretation is both flawed and scary.
Very much agree. This reminded me of Project Cybersyn [1], an attempt by socialist Chile to build a central heavily-computerized room that would summarize their entire economy to a few men literally pushing the buttons. Complete with 70s aesthetics and Star Trek TOS feel.
[1] https://thereader.mitpress.mit.edu/project-cybersyn-chiles-r...
Not until it's context window and attention is infinite.
It's best at summarizing/processing modest amount of information quickly. But given more, its usefulness drastically decreases. This demand toolings that divide the amount of information and flow.
“Not until it is context window”???
this has exceedingly obvious limits. The primary limit is the context pollution that happens when you give it too much context.
Elon and the rest of AI crew who claim LLMs can just forever grow is not realistic or held out by real world testing.
It can do "everything" but by everything, it'll still be fine tuned and harnessed and agentified which isn't really the idea that the model can do everything.