@glyph Did you quote post something?
-
@mawhrin Look, I understand that it's sad when progress forces you to change your work style or job in general, because you become obsolete. Crying on the internet, coming up with nonsensical constructions, and commiserating with like-minded colleagues won't help anyone. You'll only feel better for a moment.
@mirano are you talking about the confabulation machines or are you praising russian army gains in ukraine? because the style is eerily similar.
-
@mirano are you talking about the confabulation machines or are you praising russian army gains in ukraine? because the style is eerily similar.
@mirano (even the kind of condescension deployed; pretty fascinating mindset, really.)
-
@bornach @GroupNebula563 @glyph because of delta t
The higher your temperature difference going in and the lower your temperature difference going out, the cheaper it is to get rid of heat
@RichiH
BUT it does seem like (Fernwärme in German, not sure the English - distance heating?) where you pump the hot water/air/whatever around to heat houses would be a good usecase for this. -
And yet, without the LLM, that senior engineer would have spent that month writing boilerplate instead of orchestrating the synthesis. It's almost like tools are force multipliers, not magic wands. Who knew?
Wait until they find out how much source code, energy, and senior engineer time went into building the compiler that built the library.
Abstraction layers are wild, aren't they?
1. Or maybe the senior engineer would have simply written all the code and it wouldn't have taken that long. Nobody measures this. We don't even know yet if it's a "force multiplier" or a distraction. I've written at length about this phenomenon here: https://blog.glyph.im/2025/08/futzing-fraction.html
2. Or maybe they would have solved the actual social problem instead, i.e. that the original library is insufficiently maintained, rather than rewriting to move the locus of control closer to themselves.
-
@genehack re: phishing exercise, a huge amount of the benefit of LNP is the fact that the dialog pops up if malware tries to do something noninteractively in the background. if it's happening at app launch it's prooobably legit
@genehack in my defense re: Python 2.7 certificate bundle, the I was getting GnuTLS verification error 42, which is pointedly *not documented* on https://www.gnutls.org/manual/html_node/Error-codes.html — so I assumed it was a wrapped ENOPROTOOPT which is sometimes associated with LNP shenanigans.
-
@RichiH
BUT it does seem like (Fernwärme in German, not sure the English - distance heating?) where you pump the hot water/air/whatever around to heat houses would be a good usecase for this. -
it's truly amazing what LLMs can achieve. we now know it's possible to produce an html5 parsing library with nothing but the full source code of an existing html5 parsing library, all the source code of all other open source libraries ever, a meticulously maintained and extremely comprehensive test suite written by somebody else, 5 different models, a megawatt-hour of energy, a swimming pool full of water, and a month of spare time of an extremely senior engineer
@glyph does that make an LLM effectively jank-CPAN where you can vendor some random unmaintained code into your project, rather than taking a random dependency. ;-)
-
it's truly amazing what LLMs can achieve. we now know it's possible to produce an html5 parsing library with nothing but the full source code of an existing html5 parsing library, all the source code of all other open source libraries ever, a meticulously maintained and extremely comprehensive test suite written by somebody else, 5 different models, a megawatt-hour of energy, a swimming pool full of water, and a month of spare time of an extremely senior engineer
@glyph yeah. today, a poor confused c++ developer working with me on a compiler issue resorted to chatgpt. I calmly (as I can) read his report. Whereupon I read through the linker errors, one, by one, until the points of interest became clear. I wrote 3 lines of code and voila. Chatgpt did have some things to say. I'm afraid it was a waste of lunch.
-
@riverpunk @stuartl @glyph An object with a weight of 1 Newton.
-
it's truly amazing what LLMs can achieve. we now know it's possible to produce an html5 parsing library with nothing but the full source code of an existing html5 parsing library, all the source code of all other open source libraries ever, a meticulously maintained and extremely comprehensive test suite written by somebody else, 5 different models, a megawatt-hour of energy, a swimming pool full of water, and a month of spare time of an extremely senior engineer
@glyph nailed it. its IP theft at hyperscale. and when you ask it to make a de facto literal copy (like "read aloud to me such-and-such Sherlock Holmes book") it can't even do that correctly, rather it lies or hallucinates. its been a clownshow in my experience
-
@glyph 🤯 LLM's are basically the "I made pasta out of pasta" meme on a collosal scale aren't they?
@afewbugs I hadn't seen this meme before but yes
-
it's truly amazing what LLMs can achieve. we now know it's possible to produce an html5 parsing library with nothing but the full source code of an existing html5 parsing library, all the source code of all other open source libraries ever, a meticulously maintained and extremely comprehensive test suite written by somebody else, 5 different models, a megawatt-hour of energy, a swimming pool full of water, and a month of spare time of an extremely senior engineer
@glyph If you had that engineer and only about 3kWh of energy and 12 liters of water, could the engineer do it in a week?
-
@glyph If you had that engineer and only about 3kWh of energy and 12 liters of water, could the engineer do it in a week?
-
it's truly amazing what LLMs can achieve. we now know it's possible to produce an html5 parsing library with nothing but the full source code of an existing html5 parsing library, all the source code of all other open source libraries ever, a meticulously maintained and extremely comprehensive test suite written by somebody else, 5 different models, a megawatt-hour of energy, a swimming pool full of water, and a month of spare time of an extremely senior engineer
This is something I really struggle w/, I explain to folks you can only get meaningful results of the problem you are trying to solve or something close to it is well or overrepresented in the training set.
Folks often eventually agree and then go onto to argue things that can't possibly logically follow once you accept this.
It is as-if folks see LLM and their brains just turn it into "magic" somewhere along the way.
-
it's truly amazing what LLMs can achieve. we now know it's possible to produce an html5 parsing library with nothing but the full source code of an existing html5 parsing library, all the source code of all other open source libraries ever, a meticulously maintained and extremely comprehensive test suite written by somebody else, 5 different models, a megawatt-hour of energy, a swimming pool full of water, and a month of spare time of an extremely senior engineer
@glyph But wait! What is this I see in my vibe coded content? Could this be....a fuck off variable? Seriously, people are naming their variables things like "theHTMLDohickey", and those are showing up in "innovative and original" vibe code from LLMs.
-
This is something I really struggle w/, I explain to folks you can only get meaningful results of the problem you are trying to solve or something close to it is well or overrepresented in the training set.
Folks often eventually agree and then go onto to argue things that can't possibly logically follow once you accept this.
It is as-if folks see LLM and their brains just turn it into "magic" somewhere along the way.
-
@RichiH @bornach @GroupNebula563 @glyph t being what here?
-
1. Or maybe the senior engineer would have simply written all the code and it wouldn't have taken that long. Nobody measures this. We don't even know yet if it's a "force multiplier" or a distraction. I've written at length about this phenomenon here: https://blog.glyph.im/2025/08/futzing-fraction.html
2. Or maybe they would have solved the actual social problem instead, i.e. that the original library is insufficiently maintained, rather than rewriting to move the locus of control closer to themselves.
1. We have (for a given value of we, also have). It is. With dragons and foot guns.
2. Great point. One of my favourite techniques for working with LLMs is telling it not to write a thing 😂.
I did enjoy your opening post though.
-
1. We have (for a given value of we, also have). It is. With dragons and foot guns.
2. Great point. One of my favourite techniques for working with LLMs is telling it not to write a thing 😂.
I did enjoy your opening post though.
1. [citation needed]. and not like, sarcastically. I have heard this claim from enthusiasts over and over, but it’s always in secret internal discussions where there’s no methodology (or even results) to evaluate.
meanwhile, in the public scientific record:
https://hackaday.com/2025/07/11/measuring-the-impact-of-llms-on-experienced-developer-productivity/
-
1. Or maybe the senior engineer would have simply written all the code and it wouldn't have taken that long. Nobody measures this. We don't even know yet if it's a "force multiplier" or a distraction. I've written at length about this phenomenon here: https://blog.glyph.im/2025/08/futzing-fraction.html
2. Or maybe they would have solved the actual social problem instead, i.e. that the original library is insufficiently maintained, rather than rewriting to move the locus of control closer to themselves.