An LLM used his code editor's language server to fix a few dozen bugs in a Python rewrite
LLM used his LSP on a Python-to-ucode rewrite and fixed a few dozen bugs from interpreter/LSP errors (work deliverable).
How it works
- LLM works through the rewrite to ucode
- Reads errors from the interpreter and the language server
- Fixes a few dozen bugs as it goes
Why it’s worth knowing
The model used the same error feeds a human developer would, and fixed what they showed.
Where it’s from
Summarized from a public post on news.ycombinator.com. See the original ↗