Termsslug: code-review

Code Review

代码审查

Human checkpoint reviewing code changes for quality and correctness, now identified as the new bottleneck in AI-assisted develop

Curated Intelligence

15 items · Page 1/2
宝玉 (@dotey)T2·Agents
58 pts
Partial Code Understanding Is Normal in Large Projects and for AI Agents

Sean Goedecke argues that in large software projects, programmers understanding only the code they own is normal and is the best achievable state. Bao Yu extends this to AI agents: they too can never fully understand a codebase in one session, so quality must be backstopped by automated tests, code review, and having agents supply screenshot evidence.

Hacker News AIT2·Industry
58 pts
Stopping Code Writing Degrades Code Review Skills

The essay argues that software engineering uniquely tolerates the belief that engineers can stop writing code yet keep improving by reviewing and instructing others. Drawing analogies to deliberate practice in music and other fields, the author contends that code review judgment depends on continued hands-on coding and degrades without it.

Hacker News AIT2·Agents
78 pts
Harvard Study Finds AI Coding Agents Shift Bottleneck to Code Review

A Harvard working paper covering 718 firms finds that engineers using AI coding agents produced about 30% more code, yet completed work did not measurably increase and code took 49% longer to pass review. The authors argue the bottleneck has shifted from drafting to human review, and recommend measuring approved output, revision rates and reviewer time rather than raw code volume.

腾讯技术工程 (微信公众号)T2·Agents
62 pts
Tencent Engineer Warns AI Coding Inflates Commits Dozens of Times

A Tencent agent developer observes that AI-assisted coding has multiplied commit volume dozens of times while controllability declines: lacking the tacit knowledge humans use to trim edge cases during reviews, AI conservatively expands every exception path, inflating coordination state until review degrades into pattern matching. The author argues the bottleneck is convergence, not generation, and calls for explicit pre-generation constraints and human interrupt points.

宝玉 (@dotey)T2·Agents
58 pts
Baoyu: Requiring AI Agents to Self-Test and Screenshot Boosts Code Quality

Baoyu describes porting a team rule—PRs must include screenshots of the changed feature—to AI agents: after finishing a task, the agent self-tests and produces screenshots, often catching and fixing issues along the way. He cites Anthropic's Addy Osmani saying daily merged code changes grew from ~2,500 in May to over 30,000 by September, with humans reviewing AI-submitted evidence such as screen recordings and screenshots rather than reading every line; giving AI a way to verify its own work can improve output quality two to three times.

InfoQ 中文T2·Tools
78 pts
Harvard Study: AI Code Generation Hits Review Bottleneck, Limiting Overall Delivery Speed

A large-scale Harvard study of 718 enterprises reveals that while AI coding assistants and agents significantly boost code output (e.g., a 30% increase in lines), this does not translate into proportional gains in completed work. The bottleneck lies in the development lifecycle, where only 30-40% of time is spent on coding, with the rest consumed by planning, testing, and reviews. Data shows AI-generated code increases average merge request review time by 49%, comments by 53%, and revision rates by double, indicating that downstream bottlenecks negate upstream efficiency gains.

Hacker News AIT2·Open Source
42 pts
QGIS Bans AI-Assisted Contributions to Enforce Human Review and Policy Compliance

The QGIS project has officially banned AI-assisted code contributions via its Enhancement Proposal (QEP) process to ensure traceability and quality. The policy mandates strict human review for all Pull Requests, preventing unverified automated content from entering the core codebase. This move highlights a broader trend in open-source communities shifting from technical acceptance of LLMs to governance-focused regulation.

Ars Technica AIT2·Agents
78 pts
Study Finds AI Coding Agents Boost Code Volume But Not Software Output Due to Review Bottlenecks

A large-scale study across 700 firms reveals that while AI coding agents significantly increase code generation volume, they fail to boost overall software output or reduce employment. The primary bottleneck is human code review, where efficiency gains in the writing phase are entirely absorbed by downstream verification and correction costs.