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.
@arroz it's like watching bitcoiners talk about how they think money works
-
@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.
@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
-
@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
@zzt@mas.to @arroz@mastodon.social Ah because if it's one thing compilers are known for it's being non-deterministic 😭
-
-
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 that take you reposted is hella embarassing. thanks for pointing out another slop enthusiast to mute!
-
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.