[Supermancho]

Linus: "it keeps finding embarrassing bugs"

Linux Kernel: https://lore.kernel.org/all/CAHk-=wi4zC+Ze8e+p3tMv8TtG_80Kzs...

The idea that software has gotten so complex that a machine can evaluate code paths better than a human, seems to bristle the fur of many. Some people didn't think we would see the day where that comparative human limitation was laid bare in simpler tasks than they expected. I believe older developers are less likely to be offended, having to deal with this as a matter of course (as the mind declines).

[lilbigdoot]

I don't know why people keep acting like any kind of LLM skepticism or criticism is based on bristled fur or something.

I am very skeptical of these workflows, but I also use LLMs regularly. I specifically use them because they are better than me at sifting through massive amounts of complex information. They are also quite, uh, sketchy, for things that are significantly easier. A total mixed bag in my experience that ultimately is useful, and I will continue to use

[dd8601fn]

> They are also quite, uh, sketchy, for things that are significantly easier.

Like having real difficulty with basic counting while being able to solve extreme math problems.

Being context machines, talking about what they’re definitely good at and definitely shit at, in broad terms, has been… difficult.

[skydhash]

> The idea that software has gotten so complex that a machine can evaluate code paths better than a human, seems to bristle the fur of many

Lol! What about fuzzers, linters, typecheckers and formal tooling? There’s plenty of machine code evaluators that people do use because it’s better than relying on human skills.

The issue is the actual report and the lack of information.

[keeda]

> What about fuzzers, linters, typecheckers and formal tooling?

Pretty sure Chrome has been using all of those forever, along with some of the best security researchers in the world, yet AI (which is what GP really means by “machine” here) is finding way more bugs. I think GP’s point is that AI makes some people uncomfortable because it operates more like a human than a special purpose tool.

As for lack of information, I’m curious what you’d be interested in seeing. More information about the kinds of bugs it found perhaps?

[skydhash]

Here is a nice report about tooling

https://cacm.acm.org/research/lessons-from-building-static-a...

This is the kind of report that you can reflect upon and learn from instead of feeling like you’ve just read a marketing piece.

[keeda]

Thanks! I do believe I’ve read that piece (I worked in a similar area in a past job) it indeed is a good one. However I do think a big portion of the articles on blog.google are semi-marketing pieces, e.g. check this list: https://news.ycombinator.com/from?site=blog.google

[levkk]

There is a difference between using an electric drill and having a robot assemble the entire car.

[QuercusMax]

Or even just compilers / assemblers. They'll find all kinds of errors humans routinely overlook!

[beepbooptheory]

I don't know, this more and more feels like a sentiment projected on to people than anything real these days.. Like even in that linked thread, is personal offense like you lay out here really were you can place Laurent Pinchart's push back? You don't read anything else there at all?

And either way, what, we are going to keep this line going for another 5 years? Aren't you bored?

[Supermancho]

> You don't read anything else there at all?

The citation was in support of the post above mine and was incidentally a link to a mailing list. I did not read the mailing list threads out of personal interest, admittedly. I think it's a particularly bad way to communicate (took 15 years for me to figure it out), so I avoid them.

> Like even in that linked thread, is personal offense like you lay out here

Taking it personally, is a concrete demonstration of what I described. The replies to my comment, are unsurprising.

[beepbooptheory]

Oh huh well OK. thanks anyway?