AI

Deep, developer-first coverage of artificial intelligence — from frontier model releases and benchmarks to agents, RAG pipelines, and the AI-native tools changing how we ship software. No hype, just what actually matters to engineers.

Article 2d ago 7

Your Slack Bot's Database Is Now a Claude Session

Vercel's template wires Claude Managed Agents into Chat SDK, and the thin bridge is the point.

Rachel Goldstein

llama.cpp Finally Competes With Its Own Wrappers

With Hugging Face backing, the engine under Ollama and LM Studio now ships its own installer and model catalog.

Article · 2w ago4

Gemini's Flash Tier Is Now Google's Real Flagship

Three months after I/O 2026, Gemini 3.5 Pro is still missing while Flash keeps shipping.

Article · 2w ago1

Mistral 3 Was Never About the Leaderboard

Eight months on, the Apache-licensed family looks less like a frontier bid and more like enterprise infrastructure.

Article · 2w ago2

Go's Real AI Advantage Is the Toolchain, Not the Types

Google's pitch for agent-written Go is part marketing, part correct theory of verification. Here's which half is which.

Article · 2w ago3

Nvidia's Switchyard Finally Makes Model Routing Boring

Nemotron 3.5 Lightning gets the headlines, but the Rust proxy quietly rewires how agent workloads buy compute.

Article · 2w ago1

Nvidia's Real Product Here Is the Router, Not the Model

Nemotron 3.5 Lightning is a capable workhorse, but NeMo Switchyard targets the escalation logic every agent team keeps hand-rolling.

Article · 2w ago1

The Chain-of-Thought You Sealed Isn't Secret

A new attack replays encrypted reasoning blocks into a weaker sibling model that reads them back in plaintext.

Article · 2w ago0

macOS VMs Have Been Sandbagging Your GPU

Cua's Metal capability shim recovers up to 16x llama.cpp throughput that Apple's paravirtualized graphics was hiding.

Article · 2w ago0

Your macOS VM's GPU Was Never Slow, Just Mislabeled

A shim that lies to Metal about GPU capabilities recovers near-bare-metal llama.cpp speeds inside Apple Silicon VMs.

Article · 2w ago1

NVIDIA's Switchyard Matters More Than Its New Model

Nemotron 3.5 Lightning is a solid agent workhorse, but the open-source router is what changes agent economics.

Article · 2w ago4

There Is No Best Language for Coding Agents

Dan Luu's large-scale evals show the token-efficiency case for terse languages collapses on real tasks.

Article · 2w ago2

Local Video Generation Gets Its llama.cpp Moment

antirez's h3.c renders MiniMax's open 33B video-and-audio model in about 75 seconds on Apple Silicon.

Article · 2w ago4

Meta's Muse Glimmer Bets Open Weights on Local Agents

The 30B Apache 2.0 model fits on a 24GB GPU and quietly abandons the Llama license.

Article · 2w ago2

OpenAI Ships a Cyber Model Trained to Refuse Less

GPT-5.6-Cyber gives vetted partners exploit-grade capability, betting identity checks can do the safety work refusals used to.

Article · 2w ago0

Your Model's Knowledge Cutoff Is a Marketing Date

Cheap black-box probing shows what frontier models actually know can lag the model card by months.

Article · 2w ago0