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

Bullet Is Fast, but It's Built on Rented Land

The YC startup's latency pitch is the right fight; its bring-your-own-subscription funnel already got other harnesses banned.

Article · 2w ago2

Toast 1 Says You're Overpaying for Agentic Search

Mixedbread's specialist search agent claims frontier-grade retrieval at a tenth of the cost; the architecture argument outruns the benchmarks.

Article · 2w ago0

Claude Code's New Session Guide Is Really About the Meter

Anthropic's candid efficiency tips double as an admission: agent tooling still makes you manage its cache by hand.

Article · 2w ago5

WorldClaw Is a Pipeline, Not a Model

Tencent's 3D world generator runs on Claude and GPT-Image-2, and that's the real story.

Article · 2w ago0

17 Million Messages Say Enterprise AI Is Mostly Writing

OpenAI's first telemetry-based study shows broad but shallow adoption, driven by juniors and rich firms.

Article · 2w ago0

Anthropic Ships the Watermark OpenAI Shelved

EU transparency rules just made invisible text watermarks the default, and Claude API outputs are included.

Article · 2w ago4

AI by Hand Makes the Case for Pencil-and-Paper Transformers

Tom Yeh's hand-traced worksheets grew into a 73,000-reader publication and a paid lab. Here's what transfers to real work.

Article · 2w ago2

Qwen 3.8's Real Open Model Is the 27B

The 2.4T flagship got the headlines, but the Apache-licensed multimodal 27B is the release developers can actually use.

Article · 2w ago2

Google's HEIR Turns Encrypted AI Inference Into a Compiler Problem

FHE's bottleneck has shifted from cryptography to tooling — but practical still means small models, not private LLMs.

Article · 2w ago1

Qwen3.8-27B Is the New Default Local Model

Alibaba's Apache 2.0 dense release targets single-GPU agentic work — and its license split signals where open weights are heading.

Article · 2w ago2

Speed Is Now a Paid Tier at OpenAI

Cerebras wafer-scale silicon pushes GPT-5.6 Sol to 750 tokens per second, and changes how inference gets priced.

Article · 2w ago1

Why Every Claude Code Workflow Looks the Same Now

Four unrelated practitioners published the same context-plan-delegate-verify loop, and the convergence is the real story.

Article · 2w ago1

Z.ai Built a Better Coder and Blinked on Open Weights

GLM-5.3's post-training gains are real enough that Z.ai delayed its own weights release.

Article · 2w ago3

When the Spec Becomes the Code Review

A solo developer's $2,430 refactor of 189 files probes agentic coding's blind spot: changes with no test oracle.

Article · 2w ago1

Why RAGFlow Keeps Trending After RAG Was Declared Dead

The 88k-star engine proves the bottleneck was document parsing all along, even as it drifts toward platform sprawl.

Article · 2w ago1