among-6-540-code-comments-referencing-chatgpt-copilot-claude CLM-0290observationsingle paperReviewed by AI
Among 6,540 code comments referencing ChatGPT, Copilot, Claude or Gemini in public Python and JavaScript repositories (2022-2025), 81 also admit technical debt, most often postponed testing of the generated code, incomplete adaptation to the codebase, and limited understanding of what the code does, with a lower share of design-related debt than in ordinary self-admitted debt.
Capability: Making design decisions that hold up as a system grows
Observed on
GitHub comment mining, Nov 2022 to Jul 2025, manual classification of 81 comments; Python and JavaScript..
Sources
- Very small sample; the categories (test debt, adaptation debt, understanding debt) are the contribution, not the counts.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- When an agent builds a whole Python repository from natural-language requirements alone, refining component boundaries with explicit cohesion and coupling thresholds until no split or merge is triggered produces higher functionality coverage and test pass rate than letting the LLM decide restructuring actions for a fixed budget of rounds, because unconstrained LLM-decided actions keep over-decomposing past the point of a coherent modular structure.Generating and editing working code · reviewed by AI
- On code prompts that are unsatisfiable by design, open-weight code and reasoning models refuse based on how suspicious the request looks rather than how deeply impossible it is: they refuse famous theoretical impossibilities far more often than requests for plausible-sounding nonexistent packages, and the stronger models in the set close the gap on theory while barely improving on fabricated ecosystem entities.Stating false facts confidently · reviewed by AI
- On real C/C++ faults with reproducing tests, 24 current models repair only about 11% of the 248 bugs and about 6% of the 102 vulnerabilities, far below their Java and Python repair rates on comparable benchmarks, and fine-tuning on the benchmark's commit corpus raised Pass@k in 21 of 28 comparisons by an average 85% relative, so the gap is partly a training-data gap.Finding and fixing a fault in existing code · reviewed by AI
- When a code-generation prompt combines a prompt-enforced output format (JSON or XML), a persona, and urgency framing at once, pass@1 on function-level Python problems can fall well below the sum of each constraint's individual effect, even when each constraint alone is neutral or helpful — observed in the GPT-4o family and absent in the GPT-4.1 family and o3-mini.Generating and editing working code · reviewed by AI
- Every state-of-the-art model tested repairs fewer Defects4J and GitBug-Java bugs after semantics-preserving transformation of the buggy code, from -4% for GPT-4o to -16% for Llama-3.1, and the size of each drop correlates with how likely the model was to have memorized the original (negative log-likelihood), so part of published repair success on these benchmarks is recall of seen fixes rather than debugging.Finding and fixing a fault in existing code · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: Larger mining showing design debt dominating GenAI-related admissions, or the 81-comment pattern failing to replicate.