OpenShot 4.1 Lets You Or AI Agents Edit Video From The Command Line: Why That Matters
OpenShot 4.1 adds native text editing, Auto-Optimize for 4K footage and an experimental CLI that lets AI agents edit video from the command line.
Continue reading
Nvidia Quietly Cut Vera Rubin’s Bandwidth Targets: What The Silent Spec Change Actually Means
Nvidia cut Vera Rubin HBM4 bandwidth from 22 to 19.2 TB/s per GPU by silently editing product pages. What the revision means for the AMD race.
Continue reading
GTA 6 Dream Job: 6 Powerful Truths About Getting Paid To Play
A broadband company pays €800 for eight hours of GTA 6 at €100 an hour, plus the game. What the fine print reveals about the paid review behind the headline.
Continue reading
Stop Juggling Coding Agents In Terminal Tabs: One Open Source App Runs Them All Side By Side
Orca is a free open source agent development environment that runs coding agents side by side in isolated worktrees, with review, browser and mobile built in.
Continue reading
Baidu’s Open Source OCR Model Parses Hundred-Page Books In One Request: Here Is How SR-SWA Works
Unlimited OCR 2 is Baidu’s open source 3.3B OCR model that parses hundred-page documents in one request using SR-SWA attention. Benchmarks and limits.
Continue reading
Why Windows 11 Has So Many Web Apps: WinUI’s Missing Basics Are Finally Arriving
WinUI TableView, Chart and inking controls arrive in Windows App SDK experimental, closing the gaps that pushed Windows 11 apps to the web.
Continue reading
OpenRouter’s New Auto Router Picks Models By Where The Market Spends Its Tokens
The OpenRouter Auto router picks models by where the market spends tokens, across five cost tiers. Benchmarks, costs, session stickiness and the caveats.
Continue reading
Google Open Sourced Mantis: Security Review Skills For Coding Agents, With Warnings Attached
Mantis is Google open-source security review skills plus an ADK harness that makes coding agents find, reproduce and patch bugs, with hard isolation warnings.
Continue reading
Inspecting A Model Ran Its Code: The Unsloth Studio Finding And The Hardening That Followed
Pillar Security found model inspection in Unsloth Studio ran repository code. The disclosure, the maintainer dispute, and the remote code hardening that followed.
Continue reading
Computer-Use Agents Got A Lighter Gym: Inside Berkeley’s CUA-Lite
CUA-Lite runs computer-use agent tasks in Docker at 0.9 GB instead of a 4.1 GB VM, with unified sandboxes, data and harnesses. What it changes.
Continue reading