» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
448 posts397B MoE Model Runs on a Single RTX PRO 6000 96GB GPU
Krasis runtime runs a 397B-parameter MoE model on one RTX PRO 6000 96GB GPU, hitting 2,354 tok/s prefill via CPU-VRAM expert streaming.
Why reformatting prompts beats quantization for CPU LLM inference
Measured on a free ARM CPU box: rewriting prompts as label:value fact sheets cut LLM prefill time 6.5x while quantization tricks hurt accuracy.
What Bun's Rapid Rust Rewrite With AI Teaches Engineers
How Bun rewrote 535K lines of Zig to Rust using 64 parallel AI agents and Anthropic's Fable model in just days.
Transformers vLLM Backend Now Matches Native Inference Speed
The transformers vLLM backend now matches native inference speed via torch.fx graph analysis and automatic kernel fusion for LLMs.
Open Minis Brings a Self-Improving AI Agent to iOS and iPadOS
Open Minis pairs Apple's native APIs with a sandboxed Linux shell to deliver a self-improving, agentic AI assistant on iOS and iPadOS.
Scriptc by Vercel compiles TypeScript straight to native, no JS engine
Vercel's scriptc compiles real TypeScript into native binaries with no JS engine, matching Node byte-for-byte while cutting startup time and memory use.
Tactile Data for Robots: Five Approaches, One Unanswered Cost Question
New tactile robot datasets and models expose diverging costs for scaling contact data, alongside gains in real-time control and evaluation rigor.
metaljax Brings Unmodified JAX Code to Apple Silicon GPUs
metaljax is an open-source PJRT plugin running JAX on Apple Silicon GPUs via MLX, passing 98.4% of JAX's official test suite in beta.
Reverse-Engineering Google's Hypervisor to Close TDX Attestation Gaps
How reverse-engineering Google's proprietary TDX hypervisor closed the last gap in cloud confidential VM attestation verification.
PGSimCity: an explorable 3D city that visualizes PostgreSQL internals
PGSimCity visualizes PostgreSQL internals as an explorable 3D city, covering WAL, checkpoints, autovacuum, buffers and replication in real time.