Tag
agentic coding
Agentic coding refers to models that plan, edit, test, and iterate across a software task instead of answering a single prompt. It raises practical issues around tool use, multi-agent coordination, long contexts, token cost, and deployment choices for SWE-bench-style workflows and Claude Code-like setups.
20 articles
Devin AI Review 2026: Benchmarks, Pricing & Tests
A developer guide to testing Devin AI, its benchmarks, pricing, and workflow limits.
SpaceX收购Cursor不划算，AI编程能力应自己做
SpaceX花600亿收购Cursor并不划算，AI编程能力更该自建。
8 Cursor alternatives that fit how you work
I break down eight Cursor alternatives, what each one is actually good for, and the template I’d start from.
MiniMax M3 Proves Open-Weight Can Still Win on Coding
MiniMax M3 makes a strong case that open-weight models can still lead on coding, context, and price.
Why MiniMax M3 matters more than another long-context model
MiniMax M3 is a real step forward because it pairs long context with multimodal and agentic control.
5 GitHub Explore picks for builders
5 GitHub Explore picks show what builders are shipping, from agentic coding tools to document parsers and open-source apps.
GPT-5.0 to 5.5: Which ChatGPT Model Wins?
OpenAI’s GPT-5 family grew from a 400K-token baseline to 1M-token agentic models, with GPT-5.5 now leading benchmarks.
Why Devin AI is overrated as a software engineer
Devin AI is impressive, but it is not the autonomous software engineer its launch implied.
Sonar Acquires Gitar for AI Code Review
Sonar bought Gitar to add AI code review to SonarQube, pairing review with verification for agent-written code across CI workflows.
Zero turns compiler errors into agent-ready JSON
I break down Vercel Zero’s agent-first compiler design and give you a copy-ready template for structured diagnostics.
Why Amazon Q Developer is wrong about the future of coding
Amazon Q Developer is a strong AWS assistant, but it should not be treated as the future of software development.
MiniMax M2 opens up cheap agentic coding
MiniMax open-sourced M2, a model for agents and code that costs $0.30 per million input tokens and is free for a limited time.
Why Xiaomi’s MiMo-V2.5-Pro Changes Coding Agents More Than Chatbots
MiMo-V2.5-Pro matters because it is built for long, tool-heavy coding work, not chat.
Kimi K2.6 and Qwen 3.6 Narrow the Gap
Kimi K2.6 and Qwen 3.6 are open-weight models that now rival closed models on coding and agent tasks.
How AI Agents Spend Your Money: 1000x Tokens on SWE-bench
A study of SWE-bench Verified shows agentic coding can consume 1000x more tokens than chat, with costs driven by inputs and hard to predict.
Qwen3.6-27B opens a smaller, sharper path to coding
Qwen3.6-27B is a 27B dense multimodal model that beats Qwen3.5-397B-A17B on key coding benchmarks while staying easier to deploy.
Claude Opus 4.7 发布：更会干活了
Anthropic发布Claude Opus 4.7，长任务、视觉理解和代码工作流更强，但Token消耗也更高。
Qwen3.6-35B-A3B: 35B Open Source Model Release
Qwen3.6-35B-A3B ships with 35B total params, 3B active params, and Anthropic API compatibility for Claude Code workflows.
Cursor Composer 2 Bets on Agentic Coding
Cursor’s Composer 2 posts 61.3 on CursorBench and 61.7 on Terminal-Bench 2.0, with pricing aimed at high-volume coding teams.
Xiaomi MiMo-V2-Pro: 1T MoE Model for Agents
Xiaomi’s MiMo-V2-Pro packs 1T parameters, 42B active, and 1M context, with SWE-bench results close to Claude Sonnet 4.6.