ND Can LLMs write better code if you keep asking them to “write better code”? (minimaxir.com)
812 points by rcarmo 432 days ago | 439 comments on HN ~lite vlite-2.0
Summary ~lite
The author experiments with LLMs to optimize code, finding iterative prompting can improve code quality.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
Longitudinal · 5 evals
+1 0 −1 HN
Audit Trail 10 entries
2026-03-05 12:54 eval_success PSQ evaluated: g-PSQ=0.280 (3 dims) - -
2026-03-05 12:54 eval Evaluated by llama-4-scout-wai-psq: +0.28 (Mild positive)
2026-03-05 12:47 eval_success PSQ evaluated: g-PSQ=0.481 (3 dims) - -
2026-03-05 12:47 eval Evaluated by llama-3.3-70b-wai-psq: +0.48 (Moderate positive)
2026-02-28 23:05 eval_success Lite evaluated: Neutral (0.00) - -
2026-02-28 23:05 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral) 0.00
reasoning
ED, neutral tech blog
2026-02-28 22:59 eval_success Lite evaluated: Neutral (0.00) - -
2026-02-28 22:59 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral)
reasoning
ED, neutral tech blog
2026-02-28 22:54 eval_success Lite evaluated: Neutral (0.00) - -
2026-02-28 22:54 eval Evaluated by llama-3.3-70b-wai: 0.00 (Neutral)
reasoning
Tech blog neutral stance