npub10p…jmweu on Nostr: I often hear the analogy that #VibeCoding to generated high level code is like ...
I often hear the analogy that #VibeCoding to generated high level code is like written high level code is to machine language.
That is wrong!
Compiling is a reduction. Information is lost in the process, such as meaningful variable or class names, or comments.
When turning spec to code, on the other hand, a lot of information is added, such as naming conventions, choice of frameworks, etc.
I am not opposing the beneficial hallucination. Not at all.
All I am saying is that intent needs interpretation, and interpretation is dependent on the culture captured in the LLM. It is a nondeterministic process, inherently fragile.
Published at
2025-10-23 16:03:03 UTCEvent JSON
{
"id": "604fd3f9efb0e425a6c24affff8c178c855d97fe503ab4de88a8c27006e2f06d",
"pubkey": "78733e3b0f76f4af8de2dad93cf73a0f8431457ec4600e840ef6f0f8d9b266fb",
"created_at": 1761235383,
"kind": 1,
"tags": [
[
"t",
"VibeCoding"
],
[
"t",
"vibecoding"
]
],
"content": "I often hear the analogy that #VibeCoding to generated high level code is like written high level code is to machine language.\n\nThat is wrong!\n\nCompiling is a reduction. Information is lost in the process, such as meaningful variable or class names, or comments.\n\nWhen turning spec to code, on the other hand, a lot of information is added, such as naming conventions, choice of frameworks, etc.\n\nI am not opposing the beneficial hallucination. Not at all.\n\nAll I am saying is that intent needs interpretation, and interpretation is dependent on the culture captured in the LLM. It is a nondeterministic process, inherently fragile.",
"sig": "23496ac0e30007c51cb644c3ae3f25a25113dddf5a35ca321ea35c6c3d32ce43eebe7306329e4f0c3e446308a9aec0599f0de0d145749446ba831f1bbe654caa"
}