AI coding agents generate more code, but not more software
A recent study by Harvard researchers indicates that while AI coding agents significantly increase the volume of code generated, they do not lead to a corresponding increase in overall software output. The efficiency gains from automated coding are largely absorbed by a bottleneck in the human review process, which becomes longer and more intensive. Consequently, firms using these tools show no significant changes in software feature completion rates or employment levels.
- ▪The introduction of AI coding agents results in a 30 percent increase in total lines of code and a 23 percent rise in pull requests.
- ▪Average code review times increase by 49 percent after AI agents are introduced, with the share of pull requests requiring changes nearly doubling.
- ▪Researchers found no statistically significant change in the resolution rate of software features or overall employment levels at firms using AI tools.
- ▪The study analyzed 300 million work events from over 700,000 employees across more than 700 software development firms between 2021 and March 2026.
Hacker News (AI / LLM) files mainly under ai. We currently carry 8,043 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Ars Technica |
| Canonical URL | https://arstechnica.com/ai/2026/10/ai-coding-agents-generate-more-code-but-not-more-software/ |
| Publication time | Mon, 12 Oct 2026 02:10:20 +0000 |
| Retrieval time | 2026-10-12T02:27:58.524Z |
| Last seen | 2026-10-12T02:27:58.524Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 2woNg1uCVFXg |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Quantity, not quality AI coding agents generate more code, but not more software Study finds coding efficiency gains get “absorbed” by human review “bottleneck.” Kyle Orland – Oct 9, 2026 3:43 pm | 232 Here, let me just... yeah, can I lend you a hand here? Credit: Getty Images Here, let me just... yeah, can I lend you a hand here? Credit: Getty Images Text settings Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Minimize to nav Anyone who has even tangentially associated with computer programming knows that modern AI coding assistants and agents can be incredibly efficient at generating huge amounts of functional code.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ars Technica.
Discussion
0 commentsMore from Ars Technica
