Anyways dont worry, you are here early to the language that is going to surpass rust. I`ll make a bet with you right now. This language will be up there with the giants in roughly a month from now. Remember it --- "Kain" -- enjoy your igloo you are in right now
It`s one thing to have an AI vibe code something --- DO you want the raw exes to these benchmarks ? Download the binaries from the repo, run kain build <myfile.kn> --target llvm - boom you can see yourself. Have fun
Regarding me being a pretentious nimrod: no doubt there are many subscribers to this frame of mind.
Clarifying my structural comment: since LLMs are next token generators, they fall into the "aren't even wrong" side of lying versus truth-telling. Truth reflects a reality to which LLMs are not directly privy. Hallucinations are baked into the source. Harnesses on agents help to ground some, but they don't fully solve the issue. This doesn't make them useless. Just unreliable narrators (i.e. liars).
These benchmarks look a bit off - many times faster than C++ / Rust? Are these independently implemented?
The AI said it is faster, are you calling the AI a liar?
Anyways dont worry, you are here early to the language that is going to surpass rust. I`ll make a bet with you right now. This language will be up there with the giants in roughly a month from now. Remember it --- "Kain" -- enjoy your igloo you are in right now
It`s one thing to have an AI vibe code something --- DO you want the raw exes to these benchmarks ? Download the binaries from the repo, run kain build <myfile.kn> --target llvm - boom you can see yourself. Have fun
Always, structurally.
"Tomrod" = Pretentious nimrod.
Regarding me being a pretentious nimrod: no doubt there are many subscribers to this frame of mind.
Clarifying my structural comment: since LLMs are next token generators, they fall into the "aren't even wrong" side of lying versus truth-telling. Truth reflects a reality to which LLMs are not directly privy. Hallucinations are baked into the source. Harnesses on agents help to ground some, but they don't fully solve the issue. This doesn't make them useless. Just unreliable narrators (i.e. liars).
Oh yea just brush off the hundreds of cases in the benchmarks/ folder you dumb fuck. You aren't dealing with some vibe coder here. You are an idiot
[dead]
[dead]