And this was a debug session from hell, enormously helped by an AI
doing much of the grunt-work.
I’d like to call it my tireless helper, but the AI several times
stated flat out that this was impossible and unsolvable and that we
should just write a report about it.
I suspect those things have been trained by people who may not be
quite as stubborn as I am.
But while the AI was ready to give up several times, it did keep
adding debug code and analyzing it faithfully when I pushed. So credit
where credit is due and I let the AI write the commit message above.
IMO, this is one of the many promising sides of AI in regard to Linux development and maintenance, and it’s great to see Linus embracing it in his niche.
Skipping AI would be like refusing to use a chainsaw because you’re perfectly capable of felling a large tree with a hand axe. You can, but why spend the whole day on it when you could clear the whole forest?
With AI handling the heavy lifting across so many areas, it lets us tackle things in our niche that we’d probably simply avoid, delay, and delay, largely because of the time barrier involved.
In essence, it really amplifies what we’re already good at. As is the case here for the founder of Linux.
Exactly. The AI agent he used wanted to quit, several times, but he kept pushing it to add debug code and analyze the results. So yes the tool amplifies effort, it doesn’t replace it. Lazy input still gets you a “this is impossible” report.
This is the clearest example that humans must always persevere in pursuit of their goals, regardless of what some “Artificial Stupid” thinks is possible!
It is also the biggest justification for ensuring that our education system must focus teaching on thinking and judgement, and less emphasis on (to the point of discouraging) rote memorization, fact-gathering or source-curating!
… and, just to clarify, by “fact-gathering”, I don’t mean to discourage being informed, because proper decision-making can only take base when sufficient awareness of context is reached, and that sufficiency level is beyond the threshold that most people imagine it to be, so current decision-making is usually insufficently informed!
Never forget one of the greatest pearls of wisdom …
Those who ignore history are doomed to repeat it!
Current events in the U.S. seem to give additional verification of that truism!
Well, probably I am too philosophically minded today…
You see, I find it foolish and inappropriate not to use proper and/or better tools. There is no reason not to use a chain saw and insist on using axe instead, is there?
At the same time I belong to a generation used to (iron) axes, so to say. And I find it deeply worrying to see a person who becomes helpless and useless without his chain saw and can accomplish nothing with an axe.
Agreed @ugnvs there certainly needs to be balance. My parents insisted on NO calculator for homework, but at the same time got me a scientific calculator which I was able to access with permission. Balance is the key to everything. Not excess, not fear, or we fall behind on the useful sides of all things.
I have been using AI more recently to do problem solving myself. And one conversation included me saying something like
“Okay, you are going around in circles, let’s reset and start again.”
And after a few more prompts the answer was discovered.
So I definitely can relate.
As cannot be emphasized enough, even though AI is built to give human responses, so that we may converse and speak as if we are talking to a living being, we perfectly understand, it is just another tool. And like any other tool, we can use the acronym GIGO.
