AI CODING

New research shows Claude Code's system prompt and tool scaffolding consume 4.7x more tokens than OpenCode before processing user input. The HN thread debates whether that overhead buys better outcomes.

ByteDance's Dockerless paper asks whether coding-agent patches can be verified without spinning up per-repo environments. The practical answer is not replace CI. It is use cheaper evidence before CI.

OpenAI's GPT-5.6 Sol, Terra, and Luna tiers versus Anthropic's Claude Fable 5 and Mythos 5. Verified pricing, benchmarks, and a practical framework for picking a coding model in July 2026.

OpenAI launched ChatGPT Work to compete with Claude Cowork. Here is how they compare on features, pricing, integrations, and which workflow each handles best.

Cursor v3.11 introduces Side Chats for parallel agent conversations, Conversation Search across past sessions, and Cloud Agent Hooks for self-correcting loops. A practical guide to the new features released July 10, 2026.

A new essay argues that letting AI generate sloppy code creates a downward spiral where future AI absorbs those bad patterns. HN's 250+ comment thread is split between believers and pure vibe-coders.

A Haskell Foundation board member explains why Scarf moved to Python after 7 years in production. The culprit: LLM-driven development made Haskell's compile times an unacceptable bottleneck.

A viral post argues AI works better on standardized codebases, making rewrites economically sensible. HN pushes back with the Mythical Man-Month and maintainability concerns.

A fair comparison of AI-assisted test generation tools for coding agents - what they generate, where they plug into your workflow, and which claims to verify yourself before trusting the output.

The Bun runtime completed an AI-assisted rewrite from Zig to Rust, fixing memory safety issues and improving performance. Here is what HN thinks and why it matters for LLM-assisted code migration.

OpenAI is consolidating its desktop apps, not merging ChatGPT and Codex into one indistinguishable product. Here is how ChatGPT Work, Codex, and GPT-5.6 fit together.

xAI launched Grok 4.5, trained on trillions of Cursor interaction tokens. At $2/M input pricing, it undercuts Claude and GPT while benchmarking near Opus 4.7 level.

VS Code 1.128 shipped today with multi-chat support for Claude agent sessions. Run parallel conversations in one workspace, fork turns, compare approaches, and monitor subagents. Complete setup and workflow guide.

ZCode is Z.ai's free desktop agentic development environment tuned for GLM-5.3. Setup, Goal Mode, pricing, and how model connections work.

A controlled study of 660 Claude Code trials shows clean codebases reduce token usage by 7-8% and file revisitations by 34%, while pass rates stay the same. Traditional maintainability principles still matter in the age of AI coding.

A new SonarSource study finds clean code doesn't boost agent pass rates - but it cuts token usage by 8% and file revisitations by 34%. Here's what that means for your codebase.

OpenAI teases its most capable coding model yet - Sol Ultra uses trained subagents that communicate during tasks, reportedly hitting 91.9% on Terminal-Bench 2.1.

GPT-5.6 Sol dropped on June 26, 2026 as a limited preview with government-imposed access restrictions. Here is what developers need to know about the three-tier Sol/Terra/Luna model family, pricing, availability timeline, and how to prepare your codebase for GA.

The Program-as-Weights paper is a useful signal for developers: some LLM calls may move from per-request API prompts into compact local artifacts that behave like reusable fuzzy functions.

Dan Luu's new agentic coding essay is not another vibe check. It is a useful reminder that coding agents only compound when the test loop, review loop, and task-selection loop are stronger than the code generator.