Kevlin Henney on Nostr: Code generated from LLMs is going to need more testing than code written by ...
Code generated from LLMs is going to need more testing than code written by developers. This seems self-evident to me, but I suspect a lot of people are going to learn it (or ignore it) the hard way.
Given that most existing codebases are not well tested, and most developers don't test, this does not bode well.
Published at
2023-04-03 17:27:01Event JSON
{
"id": "8cfd6cb4af184f43115bac3da3f6ab23c17be53f97f15e190c30baa565b675cb",
"pubkey": "13ea7950fb65a144c9614b29ea006178c9a1766092fef9490cddc95dcf48bb7f",
"created_at": 1680542821,
"kind": 1,
"tags": [
[
"mostr",
"https://mastodon.social/users/kevlin/statuses/110136054377485004"
]
],
"content": "Code generated from LLMs is going to need more testing than code written by developers. This seems self-evident to me, but I suspect a lot of people are going to learn it (or ignore it) the hard way.\n\nGiven that most existing codebases are not well tested, and most developers don't test, this does not bode well.",
"sig": "b33ab89772e47f108b844c302d6aa01f481a378abfb1f440d52af069bed6e9ddc814147e992b54a6c847664ffcaefcffcc0ce095cd4cb6ca5ed13a234d9cd023"
}
