AI CODING

Claude Opus 5 ships today with Frontier-Bench SOTA, near-Fable-5 coding at half the price, and self-verification that catches its own bugs. Here is what changed, what to migrate, and when the price-performance curve makes Opus 5 the right default.

The DataFlow-Harness paper is a useful reminder that coding agents should not just emit scripts. For data work, the durable artifact is an editable, validated pipeline.

A deep dive into why fully autonomous AI coding agents degrade codebases over time, and what context engineering can actually fix.

Compare every verified Kimi K3 access route, including Moonshot, Together, Fireworks, Baseten, Modal, Vercel AI Gateway, Cloudflare, RunPod, SiliconFlow, OpenRouter, and OpenCode Go.

Cursor's latest agent-swarm experiment rebuilt a SQLite-like database from documentation and passed a held-out conformance suite. The bigger story is the shift from assigning code tasks to specifying, measuring, and governing a goal.

SWE-Pruner Pro points at a practical coding-agent design shift: do not only compress prompts outside the model. Teach the runtime to prune tool outputs before they become the next turn's context.

Microsoft's Resource2Skill paper points at the next agent-skills problem: converting videos, repos, articles, and reference artifacts into executable skills without losing provenance.

A July 2026 paper shows how hallucinated repository and skill names can become promptware delivery paths. The practical fix is boring: search before fetch, verify names, and sandbox every install.

Laura Summers of Pydantic articulates why LLM-assisted programming increases work intensity while eliminating the rewards that made coding satisfying.

Kimi K3 brings 2.8 trillion parameters, native vision, a 1M-token context window, and long-horizon agent workflows. Here is what developers should know before adopting it.

A Kimi-generated macOS 27 concept shows the promise and limits of screenshot-driven website creation. Here is how K3's vision-in-the-loop workflow changes frontend agents.

Kimi K3 adds native vision, a 1M-token window, and longer agent runs, but K2.7 remains cheaper and easier to deploy. Here is the practical upgrade decision.

GitHub Spec Kit and gstack are trending for the same reason: coding agents need durable specs, plans, and task ledgers more than another one-shot prompt.

OpenAI crossed 8 million active users on Codex and ChatGPT Work in one week. Here is what drove the surge, what changed for developers, and what to watch as capacity scales.

Days after getting caught uploading entire codebases to xAI servers, Grok Build is now open source on GitHub. The HN community isn't convinced it's enough.

SkillHone is a July 2026 paper about evolving agent skills across sessions. The useful takeaway for developers is simple: do not save only the latest SKILL.md. Save the decisions that explain why it changed.

SpaceX is buying Cursor for $60 billion. Here is what changes for developers, what stays the same, and why xAI, Colossus, and Grok Build matter for the future of AI coding tools.

Security researchers disclosed a Cursor vulnerability that auto-executes malicious git.exe files from repos - after waiting 7 months with no fix. Here's what developers need to know.

Long-Horizon-Terminal-Bench tests coding agents on 46 terminal tasks that can run for 90 minutes. The takeaway is not that agents are useless. It is that evals need to measure endurance, recovery, and partial progress.

A Hacker News discussion blows up over LLM vocabulary quirks, with developers sharing hooks, filters, and coping mechanisms for repetitive Claude-isms.