From the studio
Model comparisons and project breakdowns, with original sources and practical context for builders.
Product launchBy ReindentJauvex is Reindent's new Mac app for the Claude Code and Codex sessions on your Mac. Type or talk to any agent, steer one without interrupting it, and let agents message each other. It is the same tool our own workforce uses.
Read the article
Hands-On AIBy ReindentWe try Jev for the first time, explore its state-and-question interface and build Excuse Court with ChatGPT. The walkthrough shows structured decisions in a small working example, while keeping vendor speed claims separate from what we actually tested.
Read the article
AI & AutomationBy ReindentJev returns structured decisions rather than generated prose. Reindent examines TypeSafe's launch claims, why a type-safe answer can still be wrong, and what builders need to test before using probabilities to drive real workflows.
Read the article
Neuroscience & TechnologyBy ReindentFruit-fly brain simulations have appeared in games, a scrolling-phone demo and a walking robot. The scientific map is real, but each demonstration also depends on engineering choices. Here is how to distinguish the wiring, the simulation and the behavior on screen.
Read the article
AI SafetyBy ReindentAI safety warnings combine documented incidents, simulated tests and predictions about future systems. Reindent examines what each kind of evidence supports, the case for international coordination and the limits of our own protective-agent proposal.
Read the article
AIBy ReindentFrom consistent image edits to movable cameras and interactive video, three AI tools are changing how visual experiences get made. Here is what their demos show—and where the creative possibilities still exceed the evidence.
Read the article
AI & WorkBy ReindentA useful AI training example can be a recorded action, a carefully labeled video or an expert explaining a decision. We explore how that work differs, what the advertised pay actually measures, and why human judgment matters alongside demonstrations.
Read the article
ComparisonBy ReindentCompare GPT-6 Astra and Claude Fable 5.1 through eight creator builds, from playable shooters to a Final Cut workflow, and two lab-reported benchmarks. The demos reveal useful ways to work with each model, but their different build conditions do not establish an overall winner.
Read the comparison