@glyph Did you quote post something?
Uncategorized
903
Posts
312
Posters
0
Views
-
@glyph I missed the post where you did say that: I now see my response was rather redundant…
@justvanrossum no worries, just enthusiastically agreeing :)
-
You missed my point. My point was that people aren't moving towards LLMs but instead stopping to code all together and do other things instead...
If people were actually moving towards LLMs you'd see a lot of threads with people not understanding their own code and having to figure out the complex issues that LLM generated code causes (aka you'd see an uptick in people having to troubleshoot their own AI generated code hallucinations)...
@agowa338 @tymwol @glyph I have been trying to understand this area with precision. I think the kinds of problems the code assistants tend to fail at are the kind that were not generally answerable on StackOverflow in the first place, and which a less experienced programmer might not even recognize or be able to describe well enough to even ask a question.
-
Oh and my biggest indicator for my assumption being right is looking at all of the "AI bros" and them after a while shit talking all of the codegen stuff themselves with phrases like "what's the point of all of this when I've to hire a programmer to make it work in the end anyway?" for example...
-
Oh and my biggest indicator for my assumption being right is looking at all of the "AI bros" and them after a while shit talking all of the codegen stuff themselves with phrases like "what's the point of all of this when I've to hire a programmer to make it work in the end anyway?" for example...
@agowa338 @tymwol @glyph I've done some experimentation and I found the tools to be extremely powerful in the way having a tracked excavator is more powerful than a hand shovel. Perhaps applying it takes some skill, but it magnifies human effort quite a lot. I've grown quite concerned that many people really underestimate the impact these tools are having and will have on a secular trend of power shifting away from labor.
-
@agowa338 @tymwol @glyph I've done some experimentation and I found the tools to be extremely powerful in the way having a tracked excavator is more powerful than a hand shovel. Perhaps applying it takes some skill, but it magnifies human effort quite a lot. I've grown quite concerned that many people really underestimate the impact these tools are having and will have on a secular trend of power shifting away from labor.
-
@agowa338 @tymwol @glyph I've done some experimentation and I found the tools to be extremely powerful in the way having a tracked excavator is more powerful than a hand shovel. Perhaps applying it takes some skill, but it magnifies human effort quite a lot. I've grown quite concerned that many people really underestimate the impact these tools are having and will have on a secular trend of power shifting away from labor.
I did some experiments too. I was actually quite happy with the very first version of ChatGPT. But any iteration on it just made it less capable and worse. They optimized it for cost which heavily impacted advanced capabilities that I enjoyed.
Same for codegen. I initially thought of it as advanced Intelisense. But then the more I (tried to) use it it just become more and more annoying as it didn't even manage to suggest the right APIs of the project itself.
-
Oh and all of them failed hilariously when I tasked them with doing some negative code edits. Like typical cleanup tasks where you'd replace large chunks of codes with a single API call.
-
And I think it also had some Syntax issues. But I don't remember which programming language I tried to use it with. Probably something PowerShell or C# isch but could have been something else too...
-
@agowa338 @tymwol @glyph It's interesting, this doesn't at all line up with my experience. The tools I tried were able to translate ~1 paragraph of instruction about a change into a point by point plan with references, correctly enough to need very few edits, and then to execute it in one go. Similarly, to take a pasted error (I tried a few, the interesting one was a infrequently manifesting concurrency problem), diagnose two likely causes, and patch.
-
@agowa338 @tymwol @glyph It's interesting, this doesn't at all line up with my experience. The tools I tried were able to translate ~1 paragraph of instruction about a change into a point by point plan with references, correctly enough to need very few edits, and then to execute it in one go. Similarly, to take a pasted error (I tried a few, the interesting one was a infrequently manifesting concurrency problem), diagnose two likely causes, and patch.
@mirth @agowa338 @tymwol sometimes it does amazing things, sometimes it wastes hours of your time. is it a net benefit? unclear. it sure *does stuff* but I haven't yet seen anything that indicates it reliably does enough stuff correctly to be an improvement to efficiency. c.f.: https://blog.glyph.im/2025/08/futzing-fraction.html
-
@mirth @agowa338 @tymwol sometimes it does amazing things, sometimes it wastes hours of your time. is it a net benefit? unclear. it sure *does stuff* but I haven't yet seen anything that indicates it reliably does enough stuff correctly to be an improvement to efficiency. c.f.: https://blog.glyph.im/2025/08/futzing-fraction.html
@mirth @agowa338 @tymwol more broadly speaking, there are some strong indications that on balance it isn't delivering on its promise. A recent roundup from @davidgerard: https://pivot-to-ai.com/2025/09/09/if-ai-coding-is-so-good-where-are-the-little-apps/
-
@glyph Ow, this "title butchering" is really concerning…
-
@mirth @agowa338 @tymwol more broadly speaking, there are some strong indications that on balance it isn't delivering on its promise. A recent roundup from @davidgerard: https://pivot-to-ai.com/2025/09/09/if-ai-coding-is-so-good-where-are-the-little-apps/
@glyph @agowa338 @tymwol @davidgerard Your post is very well framed. I think you can simplify the equation to C/PH because I, W, and E are each approximately zero, and as you point out it's tricky to estimate the other numbers. If we assume for a second well-framed problems have P close to 1.0 (I suspect this is true), the major variability is C/H which I expect to be highly variable dependent similar to how some areas are easier to mechanically test than others.
-
@glyph @agowa338 @tymwol @davidgerard Your post is very well framed. I think you can simplify the equation to C/PH because I, W, and E are each approximately zero, and as you point out it's tricky to estimate the other numbers. If we assume for a second well-framed problems have P close to 1.0 (I suspect this is true), the major variability is C/H which I expect to be highly variable dependent similar to how some areas are easier to mechanically test than others.
@glyph @agowa338 @tymwol @davidgerard What I am most concerned about are what in the post you categorize as harm to the humans and 2nd order effects. I think these get to be much more concerning as the underlying tools get more effective, and I'm not sure how to even mitigate those problems. If we look at how mass media and social media have melted people's brains a bit...
-
@glyph the story in four acts we are about to see (just one example, but could be Wikipedia, or anything else as well)
-
@agowa338 @glyph @tymwol @davidgerard Is there data on that? Acknowledging that this is anecdote, I see non-programmers in my extended work and social world trying to build little apps for whatever personal purpose that I don't think they would have attempted a couple years ago. I don't think most of them even know what StackOverflow is. (and their inspiration may be all about marketing rather than actual experience, so we will see how they fare)
-
@glyph I know they have a policy about retitling posts to avoid click bait in some cases, but it seems to be a failure of reading comprehension to take this as clickbait and a joke in the introductory paragraphs to be the ‘answer’. And then extremely bad faith to then take that non-answer as a dogwhistle.
-
@mirth @agowa338 @tymwol more broadly speaking, there are some strong indications that on balance it isn't delivering on its promise. A recent roundup from @davidgerard: https://pivot-to-ai.com/2025/09/09/if-ai-coding-is-so-good-where-are-the-little-apps/
@glyph @mirth @agowa338 @tymwol @davidgerard
Maybe the 10x coders are those that couldn't code before?
-
@glyph Ow, this "title butchering" is really concerning…
@krono it's not an *entirely* unfair attempt at summarization but if I wanted people to get mad at me for somebody else naming my articles I'd go work for a newspaper
-
@krono it's not an *entirely* unfair attempt at summarization but if I wanted people to get mad at me for somebody else naming my articles I'd go work for a newspaper
@glyph Fair.
Gli ultimi otto messaggi ricevuti dalla Federazione
-
Thanks to everyone who responds or replies to my polls. They're one of my favourite parts of being on the Fediverse.
-
@zwol at this point I'd forego semantic, and just take easy and nice to look at. If I were writing a book today, I'd author it in Markdown, and then convert it to...whatever...for editing, or whatever at the very end. Before publishing, I ended up converting to an OpenOffice doc with the publishers template for editing, anyway (but I didn't originally write it to be published, it just worked out that way, so the OpenOffice step wasn't originally in the plans).
-
@ann3nova this is such a specific thing to obsess over, I love it. I drew my own pointers back then, and the one I used most looked pretty much like this. Same shape, but different colors.
-
@swelljoe I completely agree that it becomes tiring looking at all the tags. Not sure I've ever seen a markup language that was both semantic and pleasant to read in source form, though.
-
Le matematiche (libro)
@libri - La matematica è la stessa, ma la scuola russa la vede in modo diverso
-
@zwol I wrote a book in Docbook (SGML first, and then converted to XML later) about 25ish years ago, with a custom vim configuration. It wasn't pleasant. Yes, the tools were bad, but also it's just really sort of tiring looking at all the tags and the processing toolchain was dire.
I was using a LaTeX-based toolchain for the PDF generation, I don't remember details, but Sebastian Rahtz was super helpful when I ran into mysterious issues.
I wouldn't do it again. Different time, different me.
-
@jannem Yeah, like, considered as a thing-in-itself apart from the tools, the major complaint I have about DocBook is that the documentation of _how to write a book using DocBook_ is inadequate.
Many people have very similar complaints about LaTeX.
-
@Esoteria you might be a little too young for this classic scene from "WKRP in Cincinnati".
