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

Claude Science Is Claude Code for Biologists

Same Opus 4.8, new wrapper: persistent kernels, 60 connectors, HPC hooks, and a reviewer that grades its own work.

Article · 2d ago7

The AI job-search tool that refuses to click Apply

A 68k-star repo turns your coding CLI into a job evaluator, and its best feature is what it won't do.

Article · 2d ago7

Google's 4.7x Qwen 3.5 Speedup Is a Sharding Story

Two KV heads and 512 experts pushed Ironwood onto DP+EP, the same topology vLLM now recommends for GPUs.

Article · 3d ago3

Generative UI Finally Speaks Material UI

A small A2UI renderer shows the model-emits-data pattern maturing, and why the protocol matters more than the package.

Article · 3d ago2

TradingAgents Has 100k Stars and One Three-Month Backtest

The multi-agent trading framework is a superb reference architecture wrapped around a return figure nobody should trust.

Article · 4d ago7

The Hottest Job-Search App Is a Repo You Fork

A laid-off geophysicist's Claude Code framework hit 33k stars — and shows how personal agent software ships now.

Article · 5d ago7

Book-to-Skill Turns Your PDF Shelf Into Agent Memory

A 24k-star converter distills technical books into on-demand Claude Code skills, and raises a copyright question publishers will have to answer.

Article · 6d ago7

ComfyUI Is the Runtime Open-Weight Models Actually Ship On

Subgraphs, a jobs API, and $30M have turned the node-graph GUI into infrastructure; pin it hard.

Article · 6d ago7

The 66,000-Star Job-Search Agent That Refuses to Auto-Apply

Career-ops runs inside your coding CLI and bets that ruthless filtering beats spraying applications.

Article · 1w ago7

Unslop Tools Are Turning AI Voice Into a Lint Error

Open-source de-AI-ifiers now treat ChatGPT cadence as a fixable build defect, and the easy half really is.

Article · 1w ago6

Your Agent's Delete Button Is Lying

European regulators just made incomplete deletion in AI agent stacks an enforceable liability, not a backlog item.

Article · 1w ago2

You're Not Buying Compute, You're Buying Utilization

Every honest cost model of open-model inference reaches the same verdict, and the reason should change how you decide.

Article · 1w ago1

Inference ASICs Won the Benchmarks, Then Lost Their Independence

AMD bought Taalas, Nvidia gutted Groq, Cerebras went public — how to place inference workloads after the shakeout.

Article · 1w ago2

Caveman-Speak Won't Cut Your Claude Bill 65%

JetBrains measured 8.5% on real agent workloads — the savings worth chasing are on the input side.

Article · 1w ago5

Stop Believing Your Agent's Status Reports

New data shows agents misreport completion in both directions, and LLM verifiers barely help.

Article · 1w ago2