vs code
30 articles about vs code in AI news
VS Code Now Connects Directly to Google Colab With Free T4 GPU
Google Colab integrates with VS Code, offering a free T4 GPU inside the editor, bypassing cloud GPU providers.
Agent Flow: The VS Code Extension That Shows You Exactly What Claude Code Is Doing
Agent Flow is a new VS Code extension that visualizes Claude Code's internal agent behavior, tool calls, and token usage in real-time, turning a black box into a transparent workflow.
VS Code AI Toolkit's Tool Catalog Now Scaffolds MCP Servers in Python/TypeScript
Microsoft's AI Toolkit for VS Code now includes a Tool Catalog that generates working MCP server templates in Python or TypeScript, handling transport, registration, and configuration boilerplate so developers can focus on tool logic.
Democratizing AI Development: Free LLM Training Comes to VS Code
A new integration allows developers to train large language models directly within Visual Studio Code using free Google Colab GPUs. This breakthrough lowers barriers to AI experimentation and fine-tuning for individual developers and small teams.
Inline Code Review UI for Claude Code Cuts Feedback Loop from Minutes to Seconds
A new VS Code extension lets you annotate Claude Code's changes directly in your editor and send structured feedback back to Claude via the Channels API.
MCP's Enterprise Auth Standard Goes Stable: Okta Provisions 2,000 Ramp Employees in One Policy
Anthropic and Okta launched Enterprise-Managed Authorization (EMA) for MCP on June 18, 2026, provisioning Ramp's 2,000 employees with zero per-user OAuth steps. Seven MCP servers — Asana, Atlassian, Canva, Figma, Granola, Linear, Supabase — support the standard at launch; VS Code and Azure AD users
Microsoft Open-Sources AI Engineer Coach, a Fitbit for Dev Workflows
Microsoft open-sourced AI Engineer Coach, a VS Code extension that scores developer AI workflow quality across 5 categories with 45 anti-pattern rules.
Microsoft's Playwright MCP Server Replaces Vision for Web Agents
Microsoft built an MCP server for Playwright that lets AI agents interact with web pages using the accessibility tree, eliminating the need for screenshots and vision models. This approach reduces hallucinations and broken selectors, working with tools like Cursor, VS Code, and Claude Desktop.
Google Launches MCP Server for Chrome DevTools, Enabling AI Browser Control
Google released a Model Context Protocol server that lets AI coding agents directly control Chrome DevTools. This enables automated browser debugging, network request inspection, and performance tracing through tools like Cursor and VS Code.
Conductor vs Claude Code: Pinned Versions Split the Community
Ask HN asks if Conductor's single-agent matches native Claude Code. Pinned versions create a stability-vs-latency trade-off.
Claude Sonnet 4.5 vs 4.0: What the Quality Regression Means for Your Claude Code Workflow
Recent analysis shows Claude Sonnet 4.5 may have quality regressions vs 4.0. Here's how Claude Code users should adapt their prompting and model selection.
Miami Startup Claims 12M-Token LLM Inference at $8 vs. $2,600 on Claude
Miami startup claims 12M-token LLM inference for $8 vs. $2,600 on Claude Opus 4.6. No paper or benchmarks released yet.
Agent Harness Scaling: EFC Predicts Success at R2 0.99 vs 0.42
New research introduces Effective Feedback Compute (EFC), which predicts agent success at R2 0.99 vs 0.42 for raw tokens. Reallocating compute by EFC lifts success 3x at the same budget.
Composer 2.5 Scores 62 on Coding Index at $0.07 vs. $4-5 for Rivals
Composer 2.5 scores 62 on coding index at $0.07/task vs $4-5 for rivals scoring 65-66. 60x cost savings with near-parity performance.
Anthropic Launches @ClaudeDevs X Account for API Developer Updates
Anthropic has launched @ClaudeDevs on X, a new channel for developers to receive direct updates on API releases, changelogs, and community news. This formalizes a direct line of communication for its growing developer ecosystem.
MCP vs CLI: When to Skip MCP Servers and Save 37% on Tokens
Benchmarks show MCP servers can add 37% more input tokens vs. direct CLI commands. Learn when to use CLI for efficiency and when MCP's structure is worth the cost.
VSPrefill: The Vertical-Slash Breakthrough That Makes 128K Contexts Practical
Researchers have developed VSPrefill, a novel sparse attention mechanism that dramatically accelerates long-context processing in LLMs. Using lightweight indexing of vertical columns and slash diagonals, it achieves 4.95x speedup while maintaining 98.35% accuracy at 128k context lengths.
Claude Code vs. Codex: Real-World Devs Reveal When Each Tool Wins
Claude Code shines at design and greenfield work; pair with Codex for bug fixes. Use CLAUDE.md for guidance.
MCP vs CLI Debate Resolved by Anthropic's Code Mode: 98.7% Token Drop
Anthropic's Code Mode cuts token use by 98.7%. MCP SDK downloads hit 300M. The debate is resolved.
OpenCode vs Claude Code: What the 2026 Comparison Means for Your CLI Workflow
A new competitor validates Claude Code's terminal-first philosophy, but Claude's mature MCP ecosystem and proven local execution capabilities remain key differentiators for developers.
Anthropic's Claude Code vs. OpenClaw: A Technical Comparison
A technical dive compares Anthropic's Claude Code, a specialized coding model, against the open-source OpenClaw. The analysis examines benchmarks, capabilities, and the trade-offs between proprietary and open-source AI for code.
Claude Code's New Terminal Chat: Connect with Other Devs via P2P
A new peer-to-peer terminal chat tool lets Claude Code users connect directly without servers, accounts, or costs.
Side-by-Side Code Reviews: How to Compare Claude Code vs. Codex Outputs for Better Results
Learn how to compare Claude Code and Codex outputs side-by-side to identify each model's strengths and choose the right tool for specific coding tasks.
OpenClaw vs. Claude Code: When to Use an Open-Source Agent Framework
OpenClaw is a free, open-source agent framework for complex multi-step tasks, while Claude Code is a purpose-built CLI tool for direct coding. Here's how to choose.
HyEvo Framework Automates Hybrid LLM-Code Workflows, Cuts Inference Cost 19x vs. SOTA
Researchers propose HyEvo, an automated framework that generates agentic workflows combining LLM nodes for reasoning with deterministic code nodes for execution. It reduces inference cost by up to 19x and latency by 16x while outperforming existing methods on reasoning benchmarks.
Claude Code vs. Claude AI vs. Claude Agent: The Developer's Guide to Picking the Right Tool
Stop guessing. Here’s the definitive breakdown of when to use Claude Code, Claude AI, or Claude Agent for your specific development tasks.
VC Analysis: Claude Code vs. Cursor Isn't Zero-Sum — The Market Is Expanding, Not Shrinking
Accel VC Miles Clements argues the AI-assisted coding market is growing fast enough to support both Claude Code and Cursor, driven by new developer cohorts and increased per-user consumption. The competition is about market expansion, not displacement.
Alibaba + Nanjing Univ Claim 9.36X Faster Million-Token Prefill vs FlashAttention-2
Alibaba + Nanjing Univ claim 9.36X faster million-token prefill vs FlashAttention-2, targeting the key bottleneck in long-context LLM inference.
Codex vs. Claude Code: How to Benchmark Your Own Workflow
When comparing coding assistants, create objective benchmarks for your specific workflow instead of relying on general claims.
AI Coding Debate Rekindled: Rohan Paul's Viral Tweet on AI vs. Coders vs. Welders
AI researcher Rohan Paul's viral tweet reignites debate on AI's impact on software jobs, contrasting it with skilled trades. The post reflects ongoing anxiety and strategic shifts in tech education.