解读：在经过人工验证的、相对标准的 Issue 修复任务上，Qwen3 并没有展现出统治力，反而是 MiniMax 这种黑马表现抢眼。这说明在“标准题”上，各家模型差异不大，甚至 Qwen3 还有点“偏科”。

Thinking Machines Lab, led by former OpenAI CTO Mira Murati, attracts an award-winning coder, amid AI talent wars and a ...

Send a note to Doug Wintemute, Kara Coleman Fields and our other editors. We read every email. By submitting this form, you agree to allow us to collect, store, and potentially publish your provided ...

On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...

I tried a Claude Code rival that's local, open source, and completely free - how it went ...

I really wanted to believe in this free AI coding tool could replace Claude Code. But it isn't ready for prime time unless you're willing to babysit.

Vibe coding is everywhere, and it’s already drastically changing the tech industry, shaping everything from how software gets made to who gets hired. In July, WIRED's Lauren Goode went on a journey to ...

I have always taken it for granted that, just as my parents made sure that I could read and write, I would make sure that my kids could program computers. It is among the newer arts but also among the ...

You're currently following this author! Want to unfollow? Unsubscribe via the link in your email. Follow Tim Paradis Every time Tim publishes a story, you’ll get an ...

Two and a half months before extremists invaded the U.S. Capitol, the far-right wing of the internet suffered a brief collapse. All at once, in the final weeks of the country’s presidential campaign, ...