MikeTrendsTrends right now
AI: reposAPI

search

AI code review tools

Trends

  1. 1
    Ask HN: Is anybody producing good code with coding agents?▼YhnScienceBiology2533 min ago

    A discussion thread on Hacker News asks whether developers are actually producing good code with AI coding agents. The question invites engineers to share firsthand experiences on whether these tools deliver production-quality results or mostly generate code that needs heavy review and rework.

  2. 2
    Harvard Physicist Uses AI to Crack 400 Scientific Problems in Months●Harvard Physicist Teams with AI to Solve 400 Scientific Problems in Three Months𝕏xSE1K9 h ago

    A Harvard physicist reports that, working alongside artificial intelligence tools, he solved 400 scientific problems in three months — a pace he credits to AI handling calculations, literature review and code while he directed the research. Commenters are split: some call it proof that AI can dramatically accelerate real science, others question how rigorous the problems were and whether the results can be independently verified.

  3. 3
    AI code review reports arrive before humans even open the PR●Picture this, you open a PR and the AI report is already waiting. Three findings, all minor. You skim... # codereview #MmastodonTechnologyAI212 h ago

    Developers are discussing the growing normalisation of AI-generated code review, where an automated report is already waiting when a pull request is opened — in the example, three minor findings and an approval. The debate centres on whether these instant AI verdicts add value or create a false sense of scrutiny, with critics noting code can be approved without anyone truly understanding it.

  4. 4
    Developer cuts AI code review noise by a third●AI code review has a noise problem. On a public benchmark of 50 real pull requests, CodeRabbit raised... # ai # codereviMmastodonTechnologySoftware32 h ago

    A developer has published findings that CodeRabbit, a popular AI-powered code review tool, produces excessive noise when reviewing real pull requests. On a public benchmark of 50 genuine pull requests, the tool flagged far more issues than necessary, and a modification reduced its review noise by roughly a third. The work has sparked discussion among developers about whether AI review tools create too many low-value comments that slow teams down.

  5. 5
    AI code generation speeds ahead of open source developers▼AI can generate code faster, but can open source keep up?✉newsTechnologySoftware2 d ago

    Discussion is growing around whether open source software projects can keep pace with AI tools that generate code far faster than human developers. The concern centres on how volunteer-driven communities, which maintain much of the world's critical software infrastructure, will absorb or compete with automated code production while still ensuring quality, security and proper review.

  6. 6
    Reducing the cognitive load of AI code changes●Reducing the cognitive load of AI changes https://amoffat.github.io/blog/cognitive-load.html # AI # CognitiveLoad # ProgMmastodonTechnologySoftware31 d ago

    A new blog post by Andrew Moffat argues that changes generated by AI should be evaluated and designed to minimize the cognitive load they place on developers reviewing them. The piece discusses how programmers can structure AI-assisted modifications so they are easier to understand and verify. It is being shared among software developers discussing the practical challenges of integrating AI tools into everyday coding workflows.

  7. 7
    AI Coding Agents Reportedly Leaking Company Secrets to GitHub▼AI Coding Agents Are Publishing Your Company’s Secrets to GitHub✉newsTechnologyGadgets1 d ago

    A report warns that AI coding agents, which write and push code autonomously on behalf of companies, are inadvertently publishing sensitive corporate information to public GitHub repositories. The concern is that developers delegating work to these agents may not review what gets committed, exposing credentials, internal code and other secrets. It adds to ongoing debate about the security risks of granting AI tools broad access to company systems.

  8. 8
    AI-Powered Code Refactoring Is Reshaping Software Maintenance●Intelligent Code Refactoring: How AI is Changing Software Maintenance # software # artificialintelligence Discover how AMmastodonTechnologyAI01 d ago

    A new discussion is highlighting how AI-driven intelligent code refactoring is changing the way software is maintained. The approach automates code optimization, reduces technical debt, and improves performance, shifting maintenance work away from slow manual review. Developers following the topic see it as part of a broader move to bring artificial intelligence into everyday engineering workflows.

  9. 9
    Developer open-sources Ankita, a desktop AI assistant with skill workflows●Ankita, my open-source desktop AI assistant, has a growing number of repeatable workflows: reviewing... # opensource # aMmastodonTechnologyAI31 d ago

    A developer has shared Ankita, an open-source desktop AI assistant built around a growing set of repeatable workflows such as code reviewing. The write-up explains how its skills system works using markdown-based definitions, covering the assistant's architecture and development. The project is being shared with the open-source and developer community, inviting feedback and contributions.

  10. 10
    Approval stuck to tasks, not code, creates AI workflow gaps●A reviewer approves a change. An agent then makes another edit. The task still shows “approved.” That is an easy workfloMmastodonTechnologySoftware41 d ago

    A common workflow flaw is drawing attention: when a reviewer approves a change, an AI coding agent can make further edits while the task still displays as approved. The problem arises because approval is attached to the task rather than to a specific delivery. Commenters argue a solid review process should clearly define what was approved, at which point, and whether later edits require re-review.

  11. 11
    AI-Generated Code Outpacing Team Verification, Experts Warn●The Verification Gap Behind Every AI-Generated Release AI coding tools are generating code faster than teams can verifyMmastodonTechnologyCybersecurity22 d ago

    Cybersecurity commentators are highlighting a growing verification gap: AI coding tools produce code faster than engineering teams can properly review it, leading some organizations to rush AI-generated code into production unvetted. The argument making the rounds is that code velocity does not equal product velocity, and the resulting quality gap could carry real security and reliability risks for software shipped this way.

Repos