Finally, a good use case for AI.

Yeah, using a kilowatt GPU for string replacement is going to be the killer feature. I probably shouldn't even be joking, people are using it like this already

▲

charcircuit 9 hours ago | parent | next [-]

When the condition for when you want to replace is hard to properly specify, AI shines for such find and replaces.

▲

Aachen 9 hours ago | parent | next [-]

This one is literally matching "innerHTML = X" and setting "setHTML(X)" instead. Not some complex data format transformation

But I can see what you mean, even if then it would still be better for it to print the code that does what you want (uses a few Wh) than doing the actual transformation itself (prone to mistakes, injection attacks, and uses however many tokens your input data is)

	▲	charcircuit 8 hours ago \| parent [-]
		That can break the site if you do the find and replace blindly. The goal here is to do the refactor without breaking the site.

▲

lelanthran 6 hours ago | parent | prev [-]

> When the condition for when you want to replace is hard to properly specify, AI shines for such find and replaces.

And, in your opinion, this is one of those cases?

	▲	charcircuit an hour ago \| parent [-]
		It is because the new API purposefully blocks things the old API did not.

▲

littlestymaar 8 hours ago | parent | prev [-]

This ship has sailed unfortunately, no later than yesterday I've seen coworkers redact a screenshot using chatGTP.

▲

josefx 10 hours ago | parent | prev [-]

Wouldn't AI be trained on data using innerHTML?

▲

Aachen 9 hours ago | parent | next [-]

My experience is that they somehow print quite modern code despite things like ES6 being too new to be standard knowledge even for me and I'm not even middle-aged yet

Maybe the last 10 years saw so much more modern code than the last cumulative 40+ years of coding and so modern code is statistically more likely to be output? Or maybe they assign higher weights to more recent commits/sources during training? Not sure but it seems to be good at picking this up. And you can always feed the info into its context window until then

	▲	skeeter2020 9 hours ago \| parent \| next [-]
		This is not my experience. Claude has been happily generating code over the past week that is full of implicit any and using code that's been deprecated for at least 2 years. >> Maybe the last 10 years saw so much more modern code than the last cumulative 40+ years of coding and so modern code is statistically more likely to be output? The rate of change has made defining "modern" even more difficult and the timeframe brief, plus all that new code is based on old code, so it's more like a leaning tower than some sort of solid foundation.
	▲	SahAssar 7 hours ago \| parent \| prev \| next [-]
		ES6 is 11 years old. It's not that new.
	▲	chrisweekly 6 hours ago \| parent \| prev [-]
		> "ES6 being too new to be standard knowledge" Huh? It's been a decade.

▲

charcircuit 9 hours ago | parent | prev | next [-]

Which is why it can easily understand how innerHTML is being used so that it can replace it with the right thing.

▲

stvltvs 9 hours ago | parent | prev [-]

Honest question: Is there a way to get an LLM to stop emitting deprecated code?

	▲	fragmede 9 hours ago \| parent [-]
		Theoretically, if you could train your own, and remove all references to the deprecated code in the training data, it wouldn't be able to emit deprecated code. Realistically that ability is out of reach at the hobbiest level so it will have to remain theoretical for at least a few more iterations of Moore's law.