[ducktective]

Please explain this "adapting". The LLM sellers' holygrail is * you just need to crank our model bro *. With this mindset, there is no adaptation needed, save a couple of weeks of getting up to speed with nuances of using the models, the / commands and integration of their APIs into your workflow.

[Autious]

Yeah i also want to know what the adaption is. Because so far all I'm seeing is removal of the natural incentive to build deeper understanding of the systems. So in the future only the people who are really curious and want to know for knowledge sake are going to know enough to deal with the blind spots of the automatons.

Knowing how the things the LLM's are touching appears to be the only skill of value. Because using these things are trivial for anyone who is familiar with computers, what adaptation and catching up is there beyond waiting and observing what works and then just applying that?

"But the LLM's will know everything" well then we aren't needed at all, just put it on a loop and leave it running. At this endpoint there's nothing to adapt to, only direct means of allocating necessary resources to yourself for subsistence.

[simonw]

You gotta ignore what the LLM sellers are saying and listen to the people who don't have a financial incentive to sell a particular message.

[ducktective]

It's not just corpo talk. The ultimate goal in LLM and AI progress is "replacement" of professional knowledge workers. In the march of the 9s of the accuracy of the generated LLM output, the engineers role would matter less and less.

It's asking engineers to "adapt" to being efficient in filling out the last 10% then 1% then 0.1% then 0.01%.