AI Briefing#code-review
The latest AI and developer news about #code-review, with the original source and a short summary.
The latest AI and developer news about #code-review, with the original source and a short summary.
The moves mark the fourth strategic M&A transaction for Cohere this year, following acquisitions of Aleph Alpha and Reliant AI.
The tool, available for macOS, Linux, Windows, and web, allows teams to review agent-generated code in shared threads using DeltaDB, a Git-compatible versioning system.
GitHub proposes a four-stage agentic workflow using Copilot to reduce the 441% increase in pull request review times caused by high AI adoption.
Developers built a closed loop that controls agent progress without writing code directly.
The update makes Devin Review the default for PRs, with a median latency of 94 seconds and new features for incremental reviews and custom checks.
The improved speed of AI implementation has increased the importance of determining task direction, structure, verification, and the scope of delegation.
OpenQodex is an open-source tool where a separate AI session reviews code changes before pushing, achieving a 98% reproduction rate for seeded bugs.
Anthropic increased productivity while maintaining code quality through a six-layer inspection structure and convergence measures.
The system achieved a 60% true-positive rate and engaged 589 engineers through a human-on-the-loop workflow.
Sphinx intercepts git push to protected branches and requires users to answer LLM-generated questions about code changes to verify understanding.
The 98% saving required combining a switch to DeepSeek V4 Flash with context compaction to fit oversized reviews within the model's deployment window.
Sphinx pauses git pushes to ask developers questions about the logic of AI-generated diffs, blocking pushes until the developer demonstrates understanding.
The framework ranks codebase improvements as the most efficient method for ensuring agent reliability, followed by static analysis, prose, and human review.
Reviews are now approximately 3x faster, completing in 6–10 minutes, with eligible Enterprise organizations able to claim at least $10,000 in credits by January 15, 2027.
To resolve AI code verification bottlenecks, the team progressed through personas, SKILL.md, and YAML-based automated verification stages.
Seemann argues that legal responsibility for AI-generated code defects will likely fall on human sign-offs, mirroring Tesla FSD liability models.
To address the surge in outputs and 'intent debt' caused by AI adoption, the article proposes elevating decision-making processes into guides and sharing context through team reviews.
A study of over 700 firms shows AI agents boost code generation by 30% but increase code review time by 49%, resulting in no significant change in overall software output.
A local-only, security-focused diff review tool that agents can control remotely.
The free, MIT-licensed app supports OpenAI, Anthropic, Gemini, OpenRouter, and local models via Ollama or LM Studio.
GitHub has released ReviewBench, an open offline benchmark for AI code review agents, constructed from an analysis of 103.9 million GitHub pull requests.
As coding agents and CLI tools proliferate, making code navigation and review more critical than writing, 'px0', an ultra-lightweight remote-first IDE that runs instantly in the browser, has been introduced.
The GitHub Podcast refuted the competitive framing of RAG, MCP, and Skills, emphasizing the importance of risk management and judgment in AI development.
GPT-5.6 Luna demonstrated high cost efficiency by finding 75% of verified bugs at only 3.6% of the cost of GPT-6 Astra, but showed inferior performance in precision and security vulnerability detection.