AI News

I ran Claude Opus 5, GPT-5.6 Sol and Grok 4.5 through four hard builds: gallery site, spreadsheet app, image codec, repo audit. Times, results, verdict.

I ran Alibaba's new 2.4T Qwen3.8-Max-Preview through 4 real coding tests. Results rival Fable 5 and Grok 4.5 — with one big catch: speed.

I ran Grok 4.5 through my usual coding tests — website builds, a Go poker sim, a site audit. It's fast, cheap, and it found a bug no other model caught.

I tested Microsoft's MAI-Code-1-Flash coding model on real projects. Fast and cheap, yes, but here's why I won't be switching from Kimi K2.7 Code.

DeepSeek V5 has no announced release date. Here's what the July 24 deprecation actually means, plus V4 Pro pricing, vision API status, and Claude vs GPT-5.

My hands-on Claude Fable 5 review. I ran my usual coding tests and it one-shotted a poker sim no model ever beat. Best coding model yet, with caveats.

I ran my usual coding tests — two websites, a poker sim, and a code audit. Here's how MiniMax M3 actually stacks up against GPT-5.5 and Opus 4.8.

Hands-on Antigravity 2.0 review: I tested Gemini 3.5 Flash on real coding tasks. Fast, impressive design — but the hidden token cost changes everything.

DeepSeek V4 is here. I ran it through a TypeScript codebase audit, a poker simulation, and two web designs. Here's how it really compares to Opus 4.7 and GPT-5.5.