The archive · Page 5 of 5
The economics, interop standards, and workflow tradeoffs reshaping how code gets written, reviewed, and shipped when AI agents share the editor with the engineer.
97–116 of 116 articles · Newest first
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 enables pseudonymous telemetry by default, collecting command paths, flags, CI context, and device IDs on 1% of invocations. Teams running gh inside Claude.
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 with Qualcomm NPU acceleration, but Google stripped MTP heads from public weights, locking peak Gemma 4 throughput to its own runtime.
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.
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 tests AI agents on 500 real GitHub bug fixes. Learn what 'resolved 49%' means, how scoring works, and the benchmark's critical blind spots.
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.
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 is a JavaScript library that embeds an AI agent directly into web pages for natural language DOM control. No extensions, Python, or headless Chrome needed.
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 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.
Anthropic's Claude Code plugin marketplace, alongside community directories like wshobson/agents, extends the assistant with skills, agents, MCP servers, and hooks.
A comprehensive exploration of Anthropic's plugin directory for Claude Code, examining its architecture, capabilities, and impact on AI-assisted software development.
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 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.
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.
GitHub Models offered free, rate-limited LLM access for prototyping. It closed to new customers in June 2026; users migrate to Azure AI Foundry or Copilot's per-token API.
How tree-sitter-backed semantic parsing transforms LLM code comprehension, powering the next generation of AI coding assistants with precise, incremental code analysis.
Fast mode delivers 2.5x faster Claude Opus responses at 6x the cost. We break down the economics after the Opus 4.7 default swap and when the premium pays off.