Newsfeed AI

Sidd Sant

May 13, 2026 • Renee Huang

0:00

/0:41

1×

Before “agents” became a buzzword, Cline was the first real agentic coding experience. Cline started with the VSCode extension and helped a generation of developers step into AI coding. It was a great VS Code extension, but as the technology evolves, it also taught us something uncomfortable: the architecture that got us there was not the modular and extensible framework we would choose for what comes next.

It was definitely the cost of b

Tony Loehr • April 15, 2026An engineer at Cline told me he was vibe coding on a road trip from his phone. His Mac was at home running Cline agents; he was checking on them from the passenger seat. Here's the setup.

What you need

Your phone and your Mac both need Tailscale installed and signed in to the same tailnet. Tailscale is a free mesh VPN; once both devices are on it, your phone can reach your Mac's local services from anywhere.

Step 1: Start Kanban on your Mac

By default, Cline's Kanban board binds to 127.0.0

Sidd Sant • April 7, 2026You're building on infrastructure you don't control, can't audit, and can't see degrading in real time.

The Invisible Dependency

For engineers, the inference vendor problem starts with a deceptively simple question: what happens when the model changes and you don't know about it?

Most engineering teams treat their inference provider like a stable API. It isn't. Model versions rotate. Performance characteristics drift. Context window handling changes. Output formats shift in subtle ways that

Tony Loehr

ProductEvery pull request in Devin Review now gets a security review. Devin catches auth bypasses and logic flaws that pattern-matching scanners miss, with full remediation from finding to fix.June 18, 20263 min read

ProductAs of June 12, 2026, access to Claude Fable 5 has been removed from Devin following Anthropic's latest announcement and the US government directive. All other models remain available, including Claude Opus 4.8 and GPT-5.5.June 9, 20261 min read

ProductThe next generation of Windsurf: a full IDE with the Agent Command Center built in for managing fleets of local and cloud agents from one surface.June 2, 20264 min read

ProductClaude Opus 4.7 (fast mode) is now available in Windsurf with the full intelligence of Opus 4.7 and ~2.5x higher output speeds.May 12, 20261 min read

Score: 4 | Comments: 0

Score: 5 | Comments: 0

Score: 103 | Comments: 62

Your newest AI agent has a GitHub handle

Rafik Anadol Studio opens Dataland, the first museum of AI arts, powered by Google Cloud and supported by Google Arts & Culture.

Score: 63 | Comments: 26

Our AI agent, built with Gemini, helps publishers get deeper insights, understand their performance and make better decisions faster.

Score: 320 | Comments: 171

Learn how GPT-5.5 Instant improves ChatGPT’s health and wellness responses with stronger reasoning, better context, clearer communication, and physician-informed evaluations.

Researchers used an OpenAI reasoning model to help diagnose rare diseases, identifying 18 new diagnoses in previously unsolved cases.

We tested both models on the same backend task and found the biggest difference was not in writing code, but in deciding what code should be written.

Score: 1 | Comments: 0

Hey HN! I'm Zach from Adam (https://adam.new/). We're building AI agents for mechanical CAD software. We’ve built the company on two fundamental beliefs:- AI will be the primary medium for creating me

Here’s how U.S. universities are using Google’s AI tools in innovative ways.

For a decade, Vercel has shaped how the web is built. Now, we’re doing the same for agents. The companies that win the next decade will build on infrastructure designed for agents from the start, and

Research in “Nature” shows our conversational AI system matches primary care physicians in complex disease management.

Access fast and secure open-weight models in the Kilo Gateway

Meet the Google Home Speaker for Gemini. Control smart home devices, manage routines, and get fast answers using natural language.

OpenAI and Molecule.one show how a near-autonomous AI chemist using GPT-5.4 improved a key drug-making reaction, advancing medicinal chemistry research.

Agents are designed to do almost any kind of work, from answering support tickets to writing code. No matter how complex the workload, how long it runs, or how many turns it takes to complete, every a

Giving your agents access to your tools, data, and services is what makes them useful. As agents perform deeper work across systems, authenticating and authorizing that access becomes central to your

Today, we are proud to introduce , an open-source agent framework for building, running, and scaling agents. eve is designed around the idea that building an agent should mean defining what it does wi

Introducing LifeSciBench, an expert-authored, expert-reviewed benchmark for evaluating how AI systems handle real-world life science research tasks and decisions.

We've removed CLI-specific deployment limits, making it easier to deploy from local machine and external CI/CD pipelines with instant feedback. Teams and AI agents can now deploy at the pace their wor

Enterprise teams can now control access to their Vercel deployments with , using their own identity provider.Vercel Passport Visitors authenticate through providers like Okta, Auth0, or any compatible

lets your apps and agents access external services like Slack, GitHub, Salesforce, and your own custom APIs without storing a long-lived provider secret in your environment. You register a connector o

is now available in public preview.eve eve is an open-source framework for building, running, and scaling agents. An agent is just a directory of files, and production comes built in: The smallest age

Today we are introducing , a platform that gives your entire company the ability to ship with AI safely, behind your access and security boundaries.Vercel for Enterprise Apps and Agents Over the past