devtake.dev

#ai-agents

RSS

Agentic AI: Claude Code, Codex, Cursor, and the tools letting models drive long-running workflows.

Meta corporate signage outside a company office building
Policy·

Meta reassigned thousands of engineers to label AI data, and the unit is in revolt

Gergely Orosz reports Meta moved a big share of its engineers into an AI data-labeling org. TechCrunch and Wired describe a revolt. Here is what is confirmed.

Illustration for OpenAI's Daybreak security program and the GPT-5.5-Cyber model
AI·

OpenAI is now using GPT-5.5 to find and patch open-source bugs at scale

OpenAI's Daybreak push pairs the new GPT-5.5 default model with GPT-5.5-Cyber, a tool that finds, validates, and patches software flaws. Here's what it does and the catch.

Vercel Ship 2026 recap promotional card on a dark background
Web·

Vercel Ship 2026 bet the keynote on agents, but the quiet shipped wins matter more today

Vercel's Ship 2026 keynote was all agents. The eve framework and enterprise stack stole the stage, but Flags, Claude Design, and signed Blob URLs are what ship today.

Diagram-style illustration of microVM browser infrastructure
Web·

A Firecracker microVM cold-starts an isolated browser in under 400ms on EC2

browser-use runs Firecracker microVMs inside ordinary EC2 boxes to spin up isolated browser sandboxes fast. Here's how the sub-second cold start works.

Gemini Intelligence interface on an Android phone
Android·

Gemini Intelligence turns Android 17 into an agent that drives your apps

Google's Android Show pitched Gemini Intelligence and AppFunctions, an MCP-style way for the assistant to call inside your apps. Here's how it works and what to watch.

A MacBook Pro beside a Surface Book, both open on a white surface, USB-C ports in view
AI·

Running a coding agent fully on Apple Silicon, no cloud, is now an off-the-shelf stack

A popular Hacker News how-to walked through a fully local coding agent on Apple Silicon. Here's the realistic 2026 stack: runner, model, and harness.

Abstract cybersecurity illustration of a glowing padlock over a circuit board, representing data protection
AI·

OpenAI added a Lockdown Mode to ChatGPT to blunt prompt-injection attacks

OpenAI shipped Lockdown Mode in ChatGPT to cut off the data-exfiltration step of prompt-injection attacks. Here's what it actually restricts and who should turn it on.

Rows of server racks inside a data center, the kind of infrastructure that runs Starlette-based AI agent endpoints
Security·

One bad Host header bypassed auth in Starlette, the routing core under millions of AI agents

A flaw in Starlette, downloaded 325M times a week, let a single Host-header character bypass path-based auth across FastAPI, vLLM, and MCP servers.

OpenAI's Codex branding over a code background, illustrating Codex expanding across the ChatGPT app.
AI·

OpenAI is putting Codex in every ChatGPT app, with six business plugins for non-coders

On June 2 OpenAI said Codex is coming to the ChatGPT app everywhere within weeks, and shipped six role-specific plugins for sales, analytics, design, and finance teams.

A developer's Emacs session in a Linux terminal, editing C source alongside a shell
AI·

Hacker News is obsessed with durable Postgres workflows and a game about clicking yes

Six dev-tooling and AI posts that climbed Hacker News in late May 2026: durable execution on plain Postgres, LLM code smells, a permission-fatigue game, Rust 1.96, and more.

A software engineer at a laptop, the kind of AI-assisted coding workflow whose token costs blew through Uber's annual budget.
AI·

Uber blew its entire 2026 AI coding budget in four months. Its COO can't prove it paid off.

Uber exhausted its full-year Claude Code budget by April. Adoption hit 84%, heavy users burn $2,000 a month, and COO Andrew Macdonald can't connect the spend to shipped features.

Aisle of dense server racks inside the CERN Computer Center
Web·

Cloudflare rebuilt Browser Run on its own Containers. Concurrency went from 30 to 120.

Cloudflare moved Browser Run off shared isolation infrastructure on May 13. The agentic-coding crowd gets four times the headless-Chrome ceiling and half the latency.

Portrait of Andrej Karpathy, whose January 26 X thread on agentic coding was distilled into the viral CLAUDE.md file.
AI·

Karpathy posted four notes about Claude Code. The CLAUDE.md they spawned has 110K GitHub stars.

Forrest Chang turned Andrej Karpathy's January coding thread into a 70-line CLAUDE.md. It now has 110,000+ stars and has trended on GitHub for 28 weeks.

An Alibaba booth at a Chinese technology trade expo, with the company's logo above a display floor.
Hardware·

Alibaba's new Zhenwu M890 chip is 3x faster and aimed straight at agent workloads

Alibaba showed the Zhenwu M890 at its Cloud Summit on May 19. 144 GB of memory, 800 GB/s interchip bandwidth, and Qwen3.7-Max riding on top.

An illustration of the Claude Code deeplink vulnerability, showing a malicious URL handler triggering a shell prompt.
Security·

A bad command-line parser turned every claude-cli:// link into a remote shell

Joernchen of 0day.click found a deeplink RCE in Claude Code. Anthropic shipped the fix in 2.1.118 the same week.

OpenAI's Codex inside the ChatGPT mobile app, showing a Codex review on a phone screen.
AI·

OpenAI's Codex moved into the ChatGPT mobile app. You can approve a diff from the train now.

OpenAI shipped Codex remote control inside the ChatGPT app for iPhone, iPad, and Android on May 14. Pair via QR; the agent runs on your laptop, the review moves to your phone.

Anthropic Object Store opengraph illustration in clay tones
AI·

Anthropic shipped Claude for Small Business with 15 prebuilt agents. Daniela Amodei is pitching the corner-store owner.

Anthropic announced Claude for Small Business on May 13 with QuickBooks, HubSpot, Canva, and DocuSign hooks. The pitch: 15 ready-to-run agents and a 10-city tour.

Airbnb office building exterior
AI·

Airbnb says AI writes 60% of its new code. Nobody has explained what that means.

Brian Chesky dropped the 60% figure on an earnings call without defining how Airbnb measures it. Google claims 75%. The independent average is 27%.