The key question: will LLMs just compound crap code quickly, or will it accumulate and accrete in useful ways?
- The key question: will LLMs just compound crap code quickly, or will it accumulate and accrete in useful ways?
- Will code get so unworkable that it collapses under its own weight?
- Or can LLMs successfully continue improving code?
- For example, Beads has grown to 248k lines of code.
- Is LLM-generated code default-diverging or default-converging?
- Different approaches of using LLMs for Elevated Engineering will have different answers.
- The race is on to find a robustly default-converging way of working with LLM coding agents.