Here[1] is a recent submission from Simon Willison using GPT-5.2 to port a Python HTML-parsing library to JavaScript in 4.5 hours. The code passes the 9,200 test cases of html5lib-tests used by web browsers. That's a workable, usable, standards-compliant (as much as the test cases are) HTML parser in <5 hours. For <$30. While he went shopping and watched TV. The Python library it was porting from was also mostly vibe-coded[2] against the same test cases, with the LLM referencing a Rust parser.
Almost no human could port 3000 lines of Python to JavaScript and test it in their spare time while watching TV and decorating a Christmas tree. Almost no human you can employ would do a good job of it for $6/hour and have it done 5 hours. How is that "ignorance or a sense of desparation" and "not actually useful"?
Almost no human could port 3000 lines of Python to JavaScript and test it in their spare time while watching TV and decorating a Christmas tree. Almost no human you can employ would do a good job of it for $6/hour and have it done 5 hours. How is that "ignorance or a sense of desparation" and "not actually useful"?
[1] https://simonwillison.net/2025/Dec/15/porting-justhtml/
[2] https://simonwillison.net/2025/Dec/14/justhtml/