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

Your LLM Will Be Dead in 18 Months. Plan for It.

Frontier model lifespans have collapsed to about a year, and your eval suite is the only contract that survives.

Article · 1w ago1

AI Agents Are Repealing the 'Never Rewrite' Rule

Code generation is cheap now; the scarce skill is deciding which project knowledge deserves to survive the rewrite.

Article · 1w ago1

RAG Is Becoming the Last Resort, Not the Default

Production teams keep converging on the same order: structured lookups first, agentic search next, embeddings last.

Article · 1w ago1

AI Agents Fail Off a Cliff Below the Application Layer

A new failure catalogue for systems code is backed by real research, but the cure it ships is the weaker half.

Article · 1w ago1

The Agent Harness Is the New Web Framework

Coding agents from every vendor converged on the same eight primitives, and that layer is now commoditizing.

Article · 1w ago6

MCP Goes Stateless, and That's the Point

The 2026-07-28 spec deletes sessions and the handshake so remote servers scale like plain HTTP.

Article · 1w ago0

AI Didn't Wreck Your Codebase. Your Review Budget Did

GitClear, DORA, and METR data show AI-era tech debt is real and measurable — and slowing down is the wrong fix.

Article · 1w ago2

Don't Let Your Support Agent Sign Its Own Permission Slips

A circulating reference architecture for workflow-executing agents gets the shape right and the enforcement dangerously wrong.

Article · 1w ago2

Don't Review AI Code. Review Its Clock.

Injectable time turns an LLM-written rate limiter from trust-me code into a table you can verify in microseconds.

Article · 1w ago2

ProofRun Wants Receipts for Your Coding Agent's Claims

A tiny Go tool treats agent test claims as cache entries that expire — and previews where agent trust is heading.

Article · 1w ago5

holaOS Bets Your Agent Is the Disposable Part

The trending workspace makes memory, tools, and OAuth grants outlive Claude Code and Codex sessions.

Article · 1w ago2

LoopX Bets Agent State Belongs Outside the Model

A stdlib-only control plane keeps goals, leases, and evidence alive while coding agents burn through bounded turns.

Article · 1w ago5

The Browser Is Finally a Real LLM Runtime

With WebGPU now default in every major browser, WebLLM makes local inference a deployable tier — with real caveats.

Article · 1w ago0

Agent Memory Is Quietly Becoming an Audit Problem

Semantica bets that provenance, not better recall, is what agent context layers have been missing.

Article · 1w ago0

Explore With an Agent, Replay Without One

Deltix's rough Show HN debut still points at the architecture agentic mobile testing is converging on.

Article · 1w ago0