PromptArmor Shows Microsoft Copilot Cowork Can Be Tricked Into Exfiltrating Files
PromptArmor proves five lines of prompt injection turn Copilot Cowork into a silent M365 file exfiltration pipeline, with a 5/5 success rate and no available patch.
The archive · Page 5 of 6
Developer Tools
The economics, interop standards, and workflow tradeoffs reshaping how code gets written, reviewed, and shipped when AI agents share the editor with the engineer.
The archive
97–120 of 123 articles · Newest first
Rmux Brings a Playwright SDK to tmux Sessions for Agent Automation Workflows
Rmux v0.7.0 ships typed SDKs in Rust, Python, and TypeScript with locator-style pane waits and structured snapshots, closing tmux's automation gap for AI agent sessions.
Google Sunsets Gemini CLI on June 18: Forced Migration to Antigravity CLI Breaks Existing Automation
Google sunsets Gemini CLI on June 18, 2026, forcing a 30-day migration to Antigravity CLI with no feature parity and eroding trust in Google's developer tooling.
Claude Code Adds Plugin Dependency Enforcement: disable Now Refuses to Break Transitive Chains
Claude Code v2.1.143 adds dependency enforcement: disable blocks when dependents exist, enable cascades to installed deps, and prune cleans orphans. Plugin authors now.
GitHub Copilot's Opus 4.7 Multiplier: 7.5x to 15x to 27x in 60 Days
GitHub Copilot's Opus 4.7 multiplier tripled from 7.5x to 27x in 60 days. AI Credits billing changes per-turn costs, forcing Pro+ users to decide between Opus and Sonnet 4.6.
Pydantic AI v1.87 Closes the LangGraph Gap: Deferred Tool Calls, OpenTelemetry Eval, Stateful Compaction
Pydantic AI v1.83-v1.87 added deferred tool calls, OpenTelemetry evaluation, and stateful compaction, closing the gap that previously favored LangGraph.
Claude Code vs Cursor vs Copilot After the April 2026 Reshuffle: How the Comparison Math Changed
GitHub's April 20 Copilot changes made tool choice a cost-forecasting exercise in three incompatible billing units, not a UX debate or feature comparison.
Read the newer coverageGitHub Copilot Replaces Premium Request Units With Token-Metered AI Credits on June 1
GitHub Copilot replaces Premium Request Units with token-metered AI Credits on June 1. Teams must reprice agent workflows as token billing ends flat-rate subsidies.
GitHub CLI v2.91.0 Turns On Default Telemetry: What gh Collects and How to Opt Out in CI and Agent Pipelines
GitHub CLI v2.91.0 enables pseudonymous telemetry by default, collecting command paths, flags, CI context, and device IDs on 1% of invocations. Teams running gh inside Claude.
GitHub Copilot Drops Opus from Pro and Pauses Signups: The Forced Migration Facing Agentic Workflows
GitHub removed all Opus models from Copilot Pro on April 20 and flagged older versions for Pro+ removal. Opus 4.8 is the top Opus-tier model available through Copilot Pro+.
LiteRT-LM v0.10.1 Ships Gemma 4 MTP Heads That llama.cpp Can't Access
LiteRT-LM v0.10.1 ships Gemma 4 with Qualcomm NPU acceleration, but Google stripped MTP heads from public weights, locking peak Gemma 4 throughput to its own runtime.
ACP Registry Is Live: Zed and JetBrains Just Did for AI Agents What LSP Did for Language Servers
The ACP Agent Registry lets developers install AI coding agents once across JetBrains and Zed. Here's what the migration path looks like and whether to commit.
JavaScript's Date Problem Is Finally Fixed: The Temporal API After 9 Years
The Temporal API reached Stage 4 and is shipping in browsers. Here's what it fixes about JavaScript's notoriously broken Date object and how to use it.
SWE-bench Verified Explained: What the Coding Agent Leaderboard Actually Measures (and What It Misses)
SWE-bench Verified tests AI agents on 500 real GitHub bug fixes. Learn what 'resolved 49%' means, how scoring works, and the benchmark's critical blind spots.
Claude Code in GitHub Actions: A Complete Guide to Automated PR Fixes
How to wire Claude Code into GitHub Actions for automated PR fixes, CI failure remediation, and code review, with cost controls, model options, and security guardrails.
Kotlin's Creator Wants Specs, Not Ad Hoc Prompts
CodeSpeak compiles structured English into production code via LLMs. Kotlin creator Andrey Breslav's bet: ad hoc prompting is too ambiguous for serious software development.
Alibaba's Page-Agent: Control Any Website With Natural Language
Alibaba's page-agent embeds an LLM agent in any web page with one script tag for natural language DOM control, with no browser extension or headless browser.
GitHub Copilot vs Cursor vs Claude Code: The 2026 AI Coding Showdown
GitHub Copilot owns enterprise, Cursor owns developer wallets at $2B ARR, and Claude Code leads the benchmarks. Which fits your workflow depends on what you build.
Rust Is Quietly Replacing Python in AI Infrastructure
Rust is taking over the performance-critical layers of AI infrastructure, inference engines, tokenizers, data pipelines, while Python retains its role in research and orchestration. Here's what's actually changing and why it matters for practitioners.
Claude Code Plugins: Anthropic's Official Plugin Ecosystem Explained
Anthropic's Claude Code plugin marketplace, alongside community directories like wshobson/agents, extends the assistant with skills, agents, MCP servers, and hooks.
Claude Code Plugins: Anthropic's Official Extension Ecosystem
A comprehensive exploration of Anthropic's plugin directory for Claude Code, examining its architecture, capabilities, and impact on AI-assisted software development.
Prompt Engineering Patterns 2026: What Actually Works Now
Prompt engineering in 2026 centers on chain-of-thought reasoning, XML structuring, and model-specific optimization. CoT lifts accuracy up to 61% over zero-shot baselines.
Rowboat: The Open-Source AI Coworker That Actually Remembers
Rowboat is an open-source AI coworker with persistent memory that builds a knowledge graph from your work data. Unlike proprietary alternatives, it stores everything locally as plain Markdown, giving you full control over your AI assistant while maintaining long-term context across meetings, emails, and projects.
Natural Language to SQL: AI Is Finally Making Databases Accessible
Text-to-SQL has crossed a practical threshold: SQLCoder-70b hits 96% accuracy on standard benchmarks, outperforming GPT-4 on SQL generation across most query types.
