howtonotcode.com

VERCEL

APR_12 // 07:12

Ship an AI Job Board in 30 Minutes with Claude, Vercel, and Upstash

A developer released a 22-file AI job board template that deploys on Vercel in minutes and costs about $5–20/month. The template packs resume upload,...

MODEL-CONTEXT-PROTOCOL-MCP

APR_11 // 06:21

MCP is becoming the standard agent-to-backend bridge, with new tooling and a few sharp edges

MCP is consolidating as the go-to bridge between AI agents and real backends, and the ecosystem just took a tangible step forward. A new MassGen rele...

REPLIT

APR_07 // 06:34

Vibe coding meets reality: fast builds, slow shipping without guardrails

AI-fueled vibe coding builds apps fast, but shipping and running them well still demand mature engineering and guardrails. Media reports show AI-buil...

GITHUB

APR_07 // 06:29

Copilot CLI adds 'Rubber Duck' cross‑model reviews and OpenTelemetry tracing you can actually use

GitHub Copilot CLI now offers an experimental cross-model “Rubber Duck” reviewer and ships meaningful OpenTelemetry hooks to observe agent runs. GitH...

GOOGLE-CLOUD

APR_04 // 06:37

Rethinking RAG: simpler memory agents vs. brittle, slow retrieval stacks

Teams are revisiting RAG architecture as memory-agent patterns promise lower latency and fewer moving parts. One engineer reports good results replac...

ANTHROPIC-CLAUDE

MAR_17 // 13:04

Agentic coding needs a harness: ship the guardrails before the agents

Coding agents are useful, but without a real harness and governance they’ll break prod faster than they help you ship. Simon Willison explains how co...

GITHUB-COPILOT-CLI

MAR_11 // 07:22

Agent stack gets real: Copilot CLI adds MCP controls, LangChain supports OpenAI compaction, Realtime 1.5 lands

Agent tooling just got more practical: Copilot CLI adds MCP and safety controls, LangChain supports OpenAI compaction, and OpenAI ships Realtime 1.5. ...

ANTHROPIC

MAR_06 // 10:24

Prompt injection poisons GitHub Actions cache and exfiltrates secrets in Cline incident

A prompt injection in Cline’s AI-powered GitHub issue triage poisoned shared caches and leaked release secrets, underscoring the need for CI/CD-grade ...

GITHUB-COPILOT-CLI

MAR_04 // 20:44

GitHub Copilot CLI GA: agentic terminal workflows and CI automation

GitHub Copilot CLI is now generally available, bringing agentic Plan/Autopilot modes to the terminal and enabling programmatic use in CI pipelines.

ANTHROPIC

FEB_10 // 10:41

Agent Skills + System Memory for Consistent, Domain-Aware Agents

Packaging domain knowledge as reusable agent skills and pairing it with system-level memory makes AI coding agents follow your conventions, integrate ...

GITHUB-COPILOT

FEB_10 // 10:35

Copilot model selection guidance with quota and UI gotchas

Microsoft outlines how to choose Copilot models by task while users report quota friction and a missing Edit mode after recent updates. A Microsoft gu...

OPENAI

FEB_03 // 18:46

OpenAI ships Codex macOS app: multi-agent command center with git worktrees and skills

OpenAI introduced the macOS-only Codex app as a "command center" to run multiple coding agents in parallel, isolate work via git worktrees, and extend...

GITHUB-COPILOT

DEC_26 // 22:14

2026 Workflow: From Coding to Forensic Engineering

A recent video argues engineers should shift from hand-writing code and tests to orchestrating AI-generated changes and rigorously validating them. Th...

GOOGLE-GEMINI

DEC_26 // 06:31

Multi-model coding via Antigravity (Gemini Flash + Claude Opus)

A video demo shows using Antigravity to alternate between Gemini Flash and Claude Opus for code generation, refactoring, and test writing in a single ...