AI coding agents
16 published articles
AI Coding Agents
How an Anthropic ban backfired and drove OpenCode to $40M ARR
OpenCode, an open-source AI coding agent, reached 4.6 million weekly active users and $40M ARR after an Anthropic clampdown on Claude usage pushed developers toward a model-agnostic alternative.
2026-07-24
Closed-loop coding agents
Alibaba built a coding model that learns from its own users. The numbers are hard to ignore.
Alibaba's new coding model Qwen-Coder-Qoder beats Cursor Composer-1 on the Qoder Bench benchmark. Production metrics show a 3.85% code retention increase, a 61.5% drop in tool errors, and a 14.5% reduction in token use. The model trains on real agent traces through a rewarder-attacker framework against reward hacking.
2026-07-23
Coding agents
Kimi K3 edges out claude fable 5 and gpt 5.6 sol on next.js code gen benchmark
Kimi K3 ties for first at 92% success rate on Next.js code tasks, finishing in under 200 seconds. AGENTS.md documentation erases gaps between top models and mid-tier ones, pushing all of them to 96%.
2026-07-18
Mission control, not remote terminal
Cursor's iOS beta turns your phone into a coding agent dispatcher
Cursor's iOS app in public beta lets developers launch AI coding agents from their phone, bridge local and cloud workflows, and get push notifications when PRs are ready. It rethinks mobile's role in software development beyond incident response.
2026-07-14