This is one of the worst takes from LLM enthusiasts.
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
What I see a lot in these AI guy circles is this kind of "magical thinking" about how things work.
And these (confidently expressed) naive takes are not only about LLMs, but also about countless other well-documented, well-researched topics like compilers.
Who are these guys?
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz To be honest, the whole take of the original post reads like slop. LLMs tend to conflate different concepts with each other and if you have no idea what you’re talking about, it will sound very convincing.
-
@arroz That take is another case of only considering the result, not why the result exists.
Also, I guess he's fine with outsourcing his "compiling" to a third party to which he has absolutely no control over.
Vibecoders are only interested in production. They don't care how they get there.
Looks like CWE's are back on the menu!
https://blog.vidocsecurity.com/blog/vibe-coding-security-vulnerabilities
-
@arroz it’s always a bit depressing when I find out about a new pocket of mediocre tech jackasses posting twitter crap on masto. all of the guys posting “LLMs are like compilers for natural language” should have their CS degrees yanked cause they’ve proven they don’t meet the academic requirements for a CS undergrad.
-
Vibe coded skyscrapers.
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz How does he think source-level debuggers will work under that analogy?
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz I know who *will* be manually reviewing the generated code: the people in the black hats.
-
@arroz “LLMs are natural language compilers”, brought to you by the same kids insisting their product is “the operating system for the web” because nothing means anything if you ignore all implementation and engineering details
-
Vibe coded skyscrapers.
@Orb2069 @aspensmonster @zzt @arroz There was a preview of that. Search the history of highrises in UK, especially the ones built in the 1960s and 1970s.
You can save so much on tall buildings by not building 2 stories of cellars those silly continental architects added to the design. Or you can just copy paste a building on top of itself to double the number of livable floors from 6 to 12, right? -
@arroz it’s always a bit depressing when I find out about a new pocket of mediocre tech jackasses posting twitter crap on masto. all of the guys posting “LLMs are like compilers for natural language” should have their CS degrees yanked cause they’ve proven they don’t meet the academic requirements for a CS undergrad.
-
@angry_drunk @zzt @arroz I despise all of my coworkers and the company I work for. I'm just going to retire early when I'm finally let go due to slopcoding and then work on limiting my life's contact with software, since it's all going to be buggy and insecure garbage. I guess I'll be a hermit and write a manifesto.
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
The trick is to get the LLM to generate a spec and an acceptance test for the change you want to make, and verify the test.
-
And executives. Seeing who are the bandwagon jumpers and who are being thoughtful about things.
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz These systems are Dunning-Kruger-as-a-service, and that thread is a textbook example of why.
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz Well put. Ambiguity is a well studied topic in the context of compilers. You won't want your code generator to be able to interpret a construct in a dozen different ways. Natural language is nothing but ambiguous.
"Then we'll constraint it accordingly". First, there are even many context free languages for which the elimination of ambiguity is impossible, and the ones for which is possible relies on typical well known techniques for them. At that point you just "innovating" by reinventing regular languages and context free languages.
Furthermore, are gcc or any compiler in llvm part of taking water from the mouths of mexican families? Does ghc put a huge amount of stress in the electrical grid of Ireland? Will a LLM generate code as correct as CompCert? Are rustc or sbcl part of an abject bubble that likely will have catastrophic effects on the economy?
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz @stroughtonsmith Totally off their rockers. Slop machine psychosis really seems to be in the air right now.
You know who is *perfectly cool* with developers continuing to write code for their apps like normal creative people? THE USERS. In fact, putting a slop-free badge on your product *is a selling point* because nobody wants this crap.
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz @stroughtonsmith
Jesus fucking Christ, these people are incompetent idiots. I’m even more glad to be out of the programming business given that these are the morons with whom I’d be interacting. Everything is going to go to shit. -
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz except that LLMs are also deterministic (they just incorporate pseudorandom bits for some variety in the prediction)
-
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
@arroz I mean... people still audit the machine code sometimes! It's not the first resort but it's on the list, and in any sufficiently complex system you need people that can chase the program logic all the way to the CPU. It stopped being common precisely because the results became supremely consistently good to the point where it became generally recognized as a bad idea to reflexively second guess the compiler.
That process has not happened with LLMs, they constantly spit out broken code.
![[object Object]](https://media.mas.to/accounts/avatars/109/287/758/133/964/366/original/0f3099c0adfb36a0.png "[object Object]"){kind=avatar}
