Search “RAG”

English translation is being prepared.

English translation is being prepared.

GitHub Podcast: Should You Read AI-Generated Code, Is RAG Dead, Did Skills Kill MCP?

The latest episode of the GitHub Podcast breaks down five hot AI claims: AI-generated code still needs to be read and owned, but the intensity of review should be risk-tiered; Skills and MCP solve different problems—the former is packaged expert knowledge, the latter is a standard for connecting tools and data; RAG is not dead—retrieval brings models closer to the answer and reduces token waste. The episode also discusses judging AI usage in hiring, and the relationship between fine-tuned models and codebase maintainability.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

Wikimedia Foundation seeks to file amicus brief in OpenAI copyright case

The Wikimedia Foundation filed a motion on October 29, 2026, with Judge Sidney H. Stein seeking to submit an amicus curiae brief in the OpenAI copyright case; the brief's main text runs 5,831 words and states that it does not take sides with either party. The brief argues that pretraining of ChatGPT's general-purpose large language models constitutes fair use, but that its RAG feature's reproduction and use of content does not constitute fair use and should comply with license terms such as Creative Commons CC BY-SA 4.0. The Foundation said that if the training stage is not recognized as fair use, AI development may be left only to the best-funded large companies, while recognizing fair use across the board would prompt publishers to lock more information behind walls.

Google and Xreal's co-developed Android XR glasses Aura go on sale, starting at $1,099

Xreal Aura, the Android XR glasses developed by Xreal in collaboration with Google, is now on sale in the US, Canada, Japan and South Korea. The 12GB+256GB version costs $1,279 and the 16GB+512GB version $1,499, with promotional prices of $1,099 and $1,299 before the end of the year; shipping begins in mid-November. It weighs about 95 grams and uses a split architecture that puts the main computing unit and battery in a wired pocket host. It is powered by Qualcomm's Snapdragon Reality Elite chip and supports Gemini voice commands, hand tracking and a 70-degree field of view. Xreal says it offers more than 150 XR apps and experiences at launch, and is also launching a controller with a Gemini button and a wireless keyboard accessory.

Attackers exploit Linux kernel and VMware ESX vulnerabilities to launch attacks

CISA has added the VMware ESX logging vulnerability (CVE-2026-41709, CVSS 2.7) and the Linux kernel Fragnesia vulnerability (CVE-2026-46300, CVSS 7.8) to its "Known Exploited Vulnerabilities" catalog, confirming that both are being actively exploited in real-world attacks. The China-linked "Warp Panda" group used the ESX vulnerability as a zero-day to erase traces, while another set of attackers used php2shell to breach 25 firewall servers and then used Fragnesia for privilege escalation. Broadcom has been providing ESX updates since the end of July, PHP developers fixed php2shell last week, and Palo Alto Networks has also warned of related risks in PAN-OS and provided a hotfix.

iX Workshop: Program efficiently and boost your coding speed with AI assistants

heise online's iX workshop "Programming More Efficiently with AI Assistants" uses GitHub Copilot as an example to guide developers through practicing prompt techniques, Spec-Driven Development and Agentic Coding, and to distinguish Vibe Coding. The course also introduces the architecture, features and pricing of Cursor, Claude Code, OpenAI Codex and Kilocode, and explains how MCP and RAG connect to external tools and your own data. The workshop takes place online on December 15–16, 2026, and is led by Rainer Stropek.