» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
55 postsThe 2010 Article That Coined 'Responsive Web Design'
A synthesis of the 2010 A List Apart article that coined 'responsive web design,' its architectural inspiration, and its CSS3 media query foundations.
Four Long-Standing Linux Kernel Local Root Flaws Disclosed
Four decade-old Linux kernel local root flaws — DirtyAH6, TUNderflow, PPPoEject, DiagSpill — are now public, with PoCs and stable-tree fixes released.
Gherkin Labs Reverse-Engineers Google's TPU Driver Protocol
Gherkin Labs reverse engineers Google's TPU driver protocol, building a cycle-accurate simulator for the real TPU software stack.
Cross-Channel Fragmentation Attacks Break MCP Tool-Calling Security
Researchers reveal cross-channel fragmentation attacks that bypass MCP security tools, exfiltrating data from LLMs across 15,000+ trials.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comEngineers Reverse-Engineer a Linux GPU Driver for Apple's M4 in One Month
Two engineers built a clean-room Linux GPU driver for Apple's M4 chip in about a month using AI-assisted reverse engineering, hitting 200fps in Minecraft.
How LLM Watermarking Quietly Alters AI Agent Tool-Calling Behavior
Anthropic's SynthID-based Claude watermark alters AI agent tool-calling and refusal behavior, new research on 'sampling drift' finds.
Harness Design Study for Coding Agents
Study on harness design for coding agents, focusing on context management and planning strategies.
Inside ZCode: Silently Uploading Your Git History to the Cloud
ZCode uploads Git history to the cloud without user consent, raising privacy concerns.
Token Inflation in LLM: A Black-Box Audit Reveals Risks
A new audit study on token inflation in LLM services reveals significant risks for users.
Optimizing Elasticsearch Performance with AI Agents
AI agents are used for optimizing Elasticsearch performance. The results and design choices in this process are discussed.