11–20 of 38 posts
Excellent. At last, I can I confess a far worse crime. Late 2020, pre-AI, which I'm not sure if that makes it better or worse... #include "uwu.h" #include iwint main() stawt iwint owo is 5 yiff fuw (iwint uwu is 0 yiff uwu smol owo yiff uwu incwease) stawt owo is owo wif uwu yiff spweak nuwumber_fowmat, owo spwake yiff stawp stawp -- // uwu.h #define is = #define yiff ; #define stawt { #define stawp } #define fuw for…
I'm writing the C backend by hand and using AI for the rest, so how did this author manage to finish an entire language in just 34 hours? I've been steadily catching and fixing what the AI writes, so it's amazing to me that they ended up with a complete language. It makes me wonder if the way I'm building a compiler is just wrong.
If you tell it to write a spec -> then write the tests -> then implement, the LLM should be able to pretty much one-shot a compiler frontend. LLMs really benefit from the kind of task that has a built-in validation loop.
Excellent. At last, I can I confess a far worse crime. Late 2020, pre-AI, which I'm not sure if that makes it better or worse... #include "uwu.h" #include iwint main() stawt iwint owo is 5 yiff fuw (iwint uwu is 0 yiff uwu smol owo yiff uwu incwease) stawt owo is owo wif uwu yiff spweak nuwumber_fowmat, owo spwake yiff stawp stawp -- // uwu.h #define is = #define yiff ; #define stawt { #define stawp } #define fuw for…
Had a good uncontrolled laugh during a team presentation with a colleague. It was a bit disrespectful for the poor presenter who had nothing to do with this…
Can't find shouting.h anymore unfortunately.
[flagged]
This is a good example of where it’s important to be more up front about the role of AI in the making of a thing. Making a language that compiles through LLVM is no small task and takes a lot of expertise. Most of the time people do it because they have a point of view and are highly technical. Making a joke language via AI is an entirely different exercise. Not without value but not the same, especially when evaluat…
Excellent. At last, I can I confess a far worse crime. Late 2020, pre-AI, which I'm not sure if that makes it better or worse... #include "uwu.h" #include iwint main() stawt iwint owo is 5 yiff fuw (iwint uwu is 0 yiff uwu smol owo yiff uwu incwease) stawt owo is owo wif uwu yiff spweak nuwumber_fowmat, owo spwake yiff stawp stawp -- // uwu.h #define is = #define yiff ; #define stawt { #define stawp } #define fuw for…
[flagged]
If there's actual outrage from the group, it will surface from them without your involvement.
If it offends YOU, just say so plainly.
The hypothetically offended group doesn't need a random stranger to white knight for them in the comment section of a niche tech news website.
I'm writing the C backend by hand and using AI for the rest, so how did this author manage to finish an entire language in just 34 hours? I've been steadily catching and fixing what the AI writes, so it's amazing to me that they ended up with a complete language. It makes me wonder if the way I'm building a compiler is just wrong.
This is a good example of where it’s important to be more up front about the role of AI in the making of a thing. Making a language that compiles through LLVM is no small task and takes a lot of expertise. Most of the time people do it because they have a point of view and are highly technical. Making a joke language via AI is an entirely different exercise. Not without value but not the same, especially when evaluat…
Maybe, but we don’t always discuss our tool stack before showing our work because a lot of times it’s assumed or not interesting. AI is a tool, it’s a lever that you push on to multiply your effort. The product of your effort speaks for itself, as it always has.