Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Linux

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 9

  1. Amp adds view-and-control access to your runner's desktop

    Amp says users can now see and control their macOS or Linux runner's desktop. The company pitches it as useful for trying native apps that Amp builds for you, such as iOS apps. You can turn on "Share This Mac's Display" under Settings › Runner in the macOS app, or start your runner with amp --no-tui --desktop. Because the Amp client connects directly to the runner, the experience is described as nearly instant when the runner is on your local network or nearby.

    Amp Chronicle · 🔥 4
  2. Local-first AI assistant Jarvis trends on GitHub with offline voice chat

    Jarvis is a privacy-focused desktop AI assistant that offers voice and text chat, personal memory, dictation and MCP tool use, and runs offline via Ollama or an OpenAI-compatible local model server on macOS, Windows and Linux. While listening it keeps a short rolling transcript of nearby speech, so when addressed by name mid-conversation it can answer using what was just discussed; its diary and knowledge graph are stored on the user's own machine. It is free for personal use with a separate commercial license, and the developer notes it is built primarily on macOS, so Windows and Linux behavior may differ and dictation is unavailable on macOS 26 and later.

    GitHub Trending · Python · 🔥 0
  3. NetBSD gets record $120K in donations as an 'AI-free' FOSS haven

    NetBSD received a record 120 donations last month totaling $120,000, more than double its original $50,000 fundraising goal — a striking figure at a time when open-source projects generally struggle for money. The Register attributes the surge to growing anti-AI sentiment in open source, noting that the Linux world keeps moving toward AI: Linus Torvalds said in July that Linux is not an anti-AI project, and Debian voted to allow AI-generated contributions. That causal explanation is a media interpretation; the reports offer no direct evidence about donors' motives.

    开源中国 · 🔥 0
  4. Epic's new 'vibe coded' Games Launcher preview is out, 46% faster than Steam

    Epic Games released a public preview of a rebuilt PC games launcher that it says was "vibe coded," describing it as faster, redesigned and now available on Linux alongside Windows and Mac. Epic claims the new launcher starts 46% faster than Steam from cold and 14% faster when restored from the system tray (a gain of about 0.06 seconds), and calls the new library "30x faster" without further detail; it says Keywords Studios ran the testing on its behalf. Epic Games Store VP and GM Martin Keely said the team rebuilt from scratch and used AI to write and review features, while developers supervised the whole process; the company suggests Unreal developers and competitive Fortnite and Rocket League players stay on the old launcher until feature parity arrives. The move follows CEO Tim Sweeney's announcement of a pivot to "AI-accelerated development," and a Bloomberg report that a director on an unannounced Disney title told staff there would be "no more hand-written code."

    The Verge AI · 🔥 11
  5. Torvalds pushes Claude Code-written patches to Linux kernel repo

    Linux creator Linus Torvalds has pushed a branch called "noref-filemap-read-with-llm" to his personal Git repository, containing patches that reduce reference-count contention in the page cache when multiple threads read small chunks of the same file. In the patch notes he says the code, test programs, review and the first draft of the cover letter were produced by an LLM coding assistant (Claude Code) under his direction, with performance measurements run on his own machine. A separate "assoc-array-fixes" tag covers readability refactoring of the kernel's associative array code, started after developer Nils Ollrogge reported a bug; testing confirmed that bug and uncovered three further defects traced back to the library's introduction to the kernel in 2013. Neither series has been merged into mainline yet, and both could move forward during the Linux 7.4 merge window.

    ZDNET AI · 🔥 0
  6. AI-generated bug reports overwhelm open source security, IBM says AI can help fix it

    Speaking at the Linux Foundation's Open Source Summit, IBM chief client innovation officer for enterprise security Jamie Thomas warned of a "tsunami in vulnerability disclosures," with roughly 66,000 unique entries expected in 2026 — about a fourfold increase over seven years ago — while time-to-exploit has shrunk from days to as little as 29 minutes. At the same time, AI-generated reports that are duplicated, low-quality or outright fake are swamping maintainers: curl shut down its HackerOne bug bounty, Google suspended its open source vulnerability rewards program, and Linus Torvalds called the Linux security mailing list "almost entirely unmanageable." Thomas argued the community should keep AI-powered vulnerability discovery but use AI to filter duplicates and bogus reports, assess severity and assist remediation, with efforts such as OpenSSF reducing the burden on maintainers.

    TechRadar · 🔥 0
  7. Torvalds calls AI a 'gateway drug' to programming, cautions on serious work

    Speaking at the Linux Foundation's Open Source Summit in Prague, Linux kernel founder Linus Torvalds called AI an interesting and useful tool — a "gateway drug" into programming that lowers the bar for newcomers who might otherwise feel ashamed of early efforts. He cautioned, however, that using AI for "real and important" work requires knowing exactly what you want and what the outcome should be, suggesting people start with toy or personal projects. He also said the flood of AI-generated vulnerability reports and patches has made the security mailing list "almost entirely unmanageable" and is stressing maintainers, with Linux partly answering an AI deluge of patches with its own AI-driven patch review.

    TechRadar · 🔥 0
  8. Google Project Zero urges emergency mitigations before formal patches

    Google Project Zero says software vendors should prepare emergency mitigation mechanisms for actively exploited vulnerabilities, rather than relying only on faster formal patches. It outlines four approaches: feature flags, input filtering, alternative update channels, and hotpatching, while noting that testing remains necessary.

    iThome 台湾 · 🔥 0
  9. Google pauses open-source bug bounty over AI-generated report surge

    Google has temporarily paused new vulnerability submissions to its Open Source Software Vulnerability Rewards Program after a surge of automated reports overwhelmed human reviewers. The company said the vast majority of these reports contained invalid information or hallucinated vulnerability data, while supply-chain and particularly dangerous flaw reports remain eligible under stated exceptions.

    TechSpot · 🔥 0

Experience and discussion from the community

Share my Linux experienceAsk about Linux

Nobody has shared their experience with Linux yet.