Skip to content

Black Friday: up to 61% off our packs until November 30.

See the packs

Blog

Blog & Insights

Practical articles on building and running AI products, agents and workflows.

All articles

    • Developer Tools

    Zed Remote Development: SSH, Tasks and Local Previews

    Keep Zed's editor interface local while working in an authorized remote development checkout. This documentation-based guide separates settings, saved task input and localhost previews, with proposed checks and clear trust and AI privacy boundaries.

    • Developer Tools

    Raycast Clipboard History: Retention, Snippets, and AI Handoffs

    Recovering a copied excerpt, maintaining reusable wording, and sending text to AI are different decisions. This documentation-based Mac guide explains Raycast retention, source-app exclusions, Snippets, paste choices, and the boundaries between local history, sync, exports, and AI processing.

    • Developer Tools

    Tiptap Persistence: JSON, HTML, and Collaborative State

    Editable JSON, rendered HTML, and collaborative Yjs state solve different persistence problems. This documentation-backed Tiptap guide explains how to choose a representation, check extension compatibility, restore deliberately, and plan tests for save acknowledgments and reconnects.

    • Developer Tools

    Hugging Face tokenizers v1: The Same-IDs Migration Matrix

    Evaluate Hugging Face tokenizers v1 with a Same-IDs Migration Matrix that separates token-ID parity, auxiliary outputs, cache behavior, and Rust performance from application latency.

    • Developer Tools

    ShadowPEFT in PEFT: The Adapter Export Decision Map

    ShadowPEFT uses PEFT's familiar training interface, but it cannot merge into base weights. This deployment guide separates attached inference from detached language-model export, explains copy=True, and defines what to measure before shipping either artifact.

    • Developer Tools

    Qdrant Supernova Benchmark: FineWeb-10B Recall Is Not Relevance

    Matching an exact vector ranking does not prove that retrieved passages answer the question. Use the Benchmark Fidelity Ladder to design bounded Supernova experiments with shard-specific ground truth, comparable operating conditions and separate relevance checks.

    • Developer Tools

    NVIDIA Warp Route Acceptance Test: How to Evaluate Warp 1.17 for GPU Simulation Python Workloads

    NVIDIA Warp 1.17 is worth evaluating for robotics, physics, and differentiable simulation workloads, but not as a headline-driven replacement for NumPy, PyTorch, or custom CUDA. This guide gives operators a seven-gate acceptance test for parity, kernel correctness, gradients, interoperability, cold starts, memory, determinism, profiling, deployment, and adopt, pilot, or wait decisions.

    • Developer Tools
    • Robotics & Physical AI

    Anthropic Model Hardware Standard: A PDCAT Playbook for Safer AI Physical Device Control

    Anthropic's Model Hardware Standard research preview points toward shared interfaces for AI-controlled physical devices, but interoperability is not the same as operational safety. This PDCAT playbook gives teams a practical acceptance test for bounded lab and manufacturing workflows, with evidence gates, rollback, and stop-use criteria.

Next step

Have something to build?

Tell us what you need. We reply with a clear scope and a fixed quote.