code review
TrialTechniques
The practice of reviewing source code changes before they are merged or released.
Why it's here
Placed in Trial: 19 article(s) of evidence from 5 source(s), led by research-stage coverage, with 3 in the last 30 days. Confidence 92%.
Evidence (19)
- 4Hacker News·9/22/2026researchArgument Against AI-Generated Code Maintainability
The article argues that AI-assisted coding can encourage developers to stop reading, writing, and understanding code, which may lead to unmaintainable software over time. It says current AI tools optimize for short-term code generation rather than long-term maintainability, architecture, or reusable function design.
- 6The New Stack·9/18/2026researchAI code review is overloading senior engineers
The article argues that heavy AI-assisted coding is shifting senior engineers from writing code to reviewing large volumes of generated pull requests, creating review bottlenecks and burnout. It says AI output is often plausible but flawed, and recommends codifying recurring review feedback into rules and tests to reduce manual review load.
- 5InfoQ·9/16/2026product_launchDuolingo Uses AI Training to Automate Code Review
Sarah Deitke describes how Duolingo paired internal AI literacy workshops with observability dashboards to encourage broader AI adoption across engineering teams. She also presents a case study where an automated pull request risk-assessment bot was used to redesign code review while maintaining defect rates and speeding delivery.
- 8The New Stack·9/9/2026securityOpenAI lets AI block engineer code merges
OpenAI has made automated security review mandatory for engineer pull requests, and its AI models can prevent a merge if they detect a vulnerability. The company also uses models for code review, regression detection, dependency upgrades, and maintenance tasks, with some internal benchmarks described as “superhuman” in code review.
- 3The New Stack·9/8/2026framework_updateExperts Debate Replacing AI Code Review
The article says engineering teams are struggling to review growing amounts of AI-generated code, and that the best verification approach is still unsettled. Two industry figures, John Bristowe and Viktor Farcic, are set to discuss whether human review or verified pipelines are better at catching bugs in AI-era development.
- 5Martin Fowler·9/2/2026framework_updateMartin Fowler Says Code Review Is Solving the Wrong Problems
Martin Fowler argues that AI-driven code generation is making traditional code review too overloaded to serve as the main quality gate. He suggests moving feedback earlier through pairing, design sessions, trunk-based development, automated testing, static analysis, fitness functions, and security scanning, while reserving review for issues that cannot be checked automatically.
- 6GitHub Blog·8/27/2026open_sourceOpenClaw maintainers share lessons on scaling and securing a viral open source project
GitHub highlights how OpenClaw, a personal AI assistant project that runs on users’ devices, rapidly grew into a massive open source repository with heavy contributor activity. The maintainers discuss managing AI-generated pull requests, welcoming new contributors, and tightening security and supply-chain practices as the project scales.
- 6InfoQ·8/24/2026framework_updateRoblox Details an Autonomous SDLC at Scale
Andrew Swerdlow explains how Roblox is scaling autonomous software development from prompt to production. The talk focuses on security sandboxes, code review exemplars, engineering infrastructure changes, and new productivity metrics to support trusted automated deployment.
- 6InfoQ·8/19/2026researchAI Code Review Creates a Knowledge-Sharing Problem
The article argues that AI-generated code is overwhelming traditional code review, making it harder for engineers to learn from one another during the review process. It introduces the idea of cognitive debt, where teams can lose shared understanding of the system if knowledge-sharing does not shift earlier in the development cycle.
- 6The New Stack·8/13/2026framework_updateCode review shifts from diff checking to product judgment
The article argues that code review is evolving beyond line-by-line bug catching into a broader decision-making process centered on judgment, collaboration, alignment, and verification. As AI can generate large amounts of code quickly, teams may need to review intent and product decisions earlier rather than only inspecting the final diff.
- 4Hacker News·8/12/2026researchBuild Wide, Ship Narrow
The article argues that AI makes it cheaper to build features, reshape designs, and split finished work into small pull requests, changing the traditional need to pre-plan code boundaries. It recommends planning the product and design first, then building on a wide branch, demoing early, and only later decomposing the code into narrow PRs based on the structure the implementation reveals.
- 6The New Stack·7/23/2026researchHow regulated organizations can safely speed up AI coding
The article argues that regulated organizations can use AI to increase software delivery speed, but only if verification becomes a continuous part of the engineering process. It highlights how AI-assisted development and agentic workflows can help domain experts and engineers collaborate more effectively while maintaining accountability, security, and compliance.
- 5GitHub Blog·7/17/2026product_launchGitHub argues AI can make small-code reviews cheaper
GitHub’s blog post says the costly part of many small feature requests is no longer writing the first patch, but debating scope before anyone tries it. It argues that AI-generated diffs can act as a quick probe, helping teams judge feasibility and ownership from evidence rather than guesswork, while still requiring human review for changes that affect contracts, security, privacy, or support burden.
- 7InfoQ·7/16/2026product_launchAWS Launches Continuum for Agentic Code Security
Amazon Web Services has introduced AWS Continuum, an integrated security platform designed to automate discovery, enforcement, and remediation across codebases, dependencies, and applications. The launch includes four agentic capabilities focused on penetration testing, code review, threat modeling, and code vulnerability management.
- 4Hacker News·7/14/2026researchWhy AI-assisted coding can break team coordination
Armin Ronacher argues that AI-assisted programming can make individual developers far more productive, but may weaken the shared understanding that large software projects depend on. He compares this to the Tower of Babel: when local changes become easy to make without human coordination, the common language of architecture, boundaries, and invariants can erode even as code continues to ship.
- 4InfoQ·7/8/2026researchMulti-Agent Systems for Reliable Software Automation
Itamar Friedman outlines how adaptive multi-agent systems can help engineering teams move beyond simple AI autocomplete toward more resilient software development workflows. The approach combines autonomous testing, intelligent code review, and arbitration to improve control and governance across the SDLC.
- 4The New Stack·7/6/2026researchDevelopers rethink code review as a bug-finding tool
The article argues that code review is often misused as a bug-finding mechanism, a role that senior engineer Mark Dominus says it is generally not suited for. Dominus and QA engineer Mikhail Golikov say review is more valuable for assessing maintainability, spotting hard-to-understand changes, and revealing when a change set is too large or complex to review effectively.
- 6InfoQ·6/29/2026researchGitLab Study Finds AI Speeds Coding but Not End-to-End Delivery
GitLab's 2026 AI Accountability Report says 78% of developers report coding faster with AI tools, but overall software delivery has not accelerated. The report points to downstream bottlenecks in testing and review, along with new enterprise concerns around governance and traceability.
- 4Martin Fowler·3/31/2026researchEncoding Team Standards for AI Coding Assistants
The article argues that instructions for AI-assisted development should be treated as versioned, reviewed infrastructure rather than ad hoc prompts. By encoding team standards for generation, refactoring, security, and review, teams can make AI output more consistent across developers.