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 1h ago 0

Gemini 3.7 Flash's Half-Price Launch Has an Expiration Date

Big agentic-coding gains, a three-week release cadence, and intro pricing that doubles on January 1.

Rachel Goldstein

Claude's Riemann Result Is Real, and the Workflow Is the Story

An unreleased model jumped a 50-year-old bound from 41.6% to 67.2% inside Claude Code, with a machine-checked proof.

Article · 3d ago2

Ante Bets Coding Agents Should Be Single Binaries

A 15MB Rust agent with llama.cpp baked in gets the architecture right and the trust model wrong.

Article · 3d ago3

Forget the Manifesto — Meta's Real News Is Apache 2.0

Muse Glimmer drops Llama's lawyered license, and that choice reveals who actually won open-weight AI.

Article · 3d ago0

Docker Finally Admits Containers Can't Contain AI Agents

Its new microVM Sandboxes make YOLO-mode coding agents safe by default, with a custom hypervisor instead of containers.

Article · 3d ago2

Muse Glimmer Is Meta's Apology for the Llama License

A dense 30B coding agent under Apache 2.0 puts Meta back in the local-model race it started and lost.

Article · 3d ago2

Muse Glimmer Is Meta's Best Open-Weights Move Since Llama 2

The 30B Apache-licensed model won't out-code the cloud, but it's engineered for the machine you actually own.

Article · 3d ago1

Docker's Answer to YOLO-Mode Agents Is a VM, Not a Container

The sbx CLI wraps coding agents in disposable microVMs with a credential-injecting proxy — and a mandatory login.

Article · 3d ago1

Claude Code's Permission Prompts Were Security Theater All Along

Anthropic's data on rubber-stamped approvals justifies the auto mode default — but the sandbox is still your job.

Article · 3d ago4

Parallel Coding Agents Are Rediscovering the Blackboard

When Claude Code sessions collide, a markdown file in git beats fancy orchestration — and a 1970s AI pattern explains why.

Article · 3d ago1

Vibe-Coded Simulations Are the New Study Notes

Coding agents make explorable explanations cheap enough to generate on demand — but self-review is not fact-checking.

Article · 4d ago0

Code Retrieval Is Converging on Graphs, Not Embeddings

A trending open-source tool turns your monorepo into a queryable knowledge graph your coding agent can call over MCP.

Article · 4d ago0

Voice AI's Hard Problems Moved Into the Framework Layer

LiveKit Agents is trending because developers are catching up to a stack that already won.

Article · 4d ago3

Latent Reasoning Escapes the Lab, Bolted Onto DeepSeek-V4

A 36M-parameter head makes V4-Flash think silently in latent space — and the serving hacks matter more than the benchmarks.

Article · 4d ago2

Your AI's Memory Problem Is Really Cache Invalidation

Memory layers for Claude Code keep multiplying, but storing context was never the hard part.

Article · 5d ago0

Meta and AWS Just Agreed on How AI Agents Should Code

Muse Code and Kiro Crew launched a day apart — and converged on the same parallel-agent architecture.

Article · 5d ago0