Comment by yubrshen
1 year ago
When asking LLM repeated improving or adding a new feature in a codebase, the most frustration risk is that LLM might wipe out already working code!
What are your strategies to prevent such destructions of LLM?
1 year ago
When asking LLM repeated improving or adding a new feature in a codebase, the most frustration risk is that LLM might wipe out already working code!
What are your strategies to prevent such destructions of LLM?
same thing a human does, stick it in git. tools like aider use git, along with heuristics on LLM output. If the working code is wiped out, give it a few more prompts to let it fix it, or revert ban to a known good/working copy.