GoKawiil
Tech News
A developer released geiger, a free command-line utility that scans a machine for installed AI agents, harnesses, MCP servers, plugins and extensions, then reports in plain language what each one can access. It runs via npx with no installation or account required, only reads configuration files and directories, and writes nothing to disk unless a JSON export is explicitly requested.
Meta rolled out Muse, a new autonomous AI agent that CEO Mark Zuckerberg says learns a user's habits and goals to handle everyday tasks like online shopping, drafting documents, filling out forms, and answering emails. Users must grant Muse permission to access their apps and data, and Meta says a separate 'Sentinel' system monitors its actions to prevent it from acting without oversight. The tool is now live in the US on iOS, Android, and via the muse.ai website.
UK-based AI consultant Grant de Swardt found his Claude Max subscription burning through tokens even when he wasn't using the service. Anthropic investigated and told him a compromised session key had been used to generate unauthorized OAuth tokens, allowing a third party to consume his allotted usage. The company suspended his account, wiped his active sessions, and issued a partial refund but could not explain how the credentials were obtained.
A hobbyist developer documented an experiment attempting to bring advanced PC-speaker-style audio techniques, including PCM and PWM sample playback, to the ZX Spectrum's single-bit beeper. The main breakthrough was getting rudimentary multichannel sound, essentially chords, to play through the one-bit speaker, though the original goal of full PC-style playback fell short.
Microsoft's latest Patch Tuesday release addresses 966 vulnerabilities, its largest batch ever, including 105 rated Critical and two zero-days already being exploited in the wild. The count excludes 204 additional flaws Microsoft patched earlier in the month across products like Azure AI Language, Copilot Studio, and Entra ID.
A developer built an experimental one-way projectional viewer that lets programmers toggle implementation detail out of view in source code without editing it back, using a Rebol phone-number parsing grammar as the test case. Rather than removing plumbing code like value-capturing and print statements, the tool simply elides them from the reading view so the underlying grammar structure stands out.
Anthropic has been ranked No. 1 on Fast Company's Best Workplaces for Innovators 2026 list, with recognition tied partly to Claude Code, a tool originally built internally for engineers to test AI models and assist with coding. The tool spread organically inside the company before Anthropic released it publicly in early 2025, later evolving into the broader Claude Cowork product launched in early 2026.
Logitech has launched the MX Keypad, a $99.99 accessory featuring nine customizable full-color LCD keys for triggering commands, macros, and AI prompts. It essentially strips down the company's pricier MX Creative Console, dropping the separate dialpad while keeping the keypad and halving the cost. The device was built in partnership with GitHub and ships with GitHub Copilot integration built in.
A developer describes discovering git worktrees—a decade-old git feature they'd never used—after noticing tools like Claude Code create a separate worktree for each task so multiple AI agents can work on the same repository in parallel. The piece explains that worktrees let you check out multiple branches into separate working directories simultaneously, all sharing the same underlying repository data, unlike traditional branch switching which requires stashing and checking out.
Coding assistants like Claude Code, Instinct, and Poke are shifting from local machines to cloud-hosted virtual machines so they can be accessed from phones. Inspection of Claude Code's setup shows it runs inside a Firecracker microVM with a custom Rust-based init process controlling the session over a vsock connection, while inference calls go out through a locked-down, MITM'd egress gateway to Anthropic's servers.
xAI's Grok Build is a terminal-based AI coding assistant that supports mouse clicks for navigation but requires an external editor like Visual Studio Code for direct code edits, unlike rivals such as Google's Antigravity that bundle a full IDE. Users can prompt it to explain a codebase, install dependencies, run a web app, or build one from scratch and get deployment guidance, then iterate with further prompts. Access depends on a Grok plan, with free users hitting token limits quickly and paid SuperGrok tiers ($30 to $300 monthly) offering higher weekly caps.
A developer found that CodePen's updated editor sends everything typed into its code fields to codepen.dev within one to two seconds, even without saving. Using a unique test marker in an HTML file, they confirmed CodePen triggered a build with save disabled and the marker still appeared verbatim in the generated preview page served from a codepen.dev subdomain.