Entries for August 26, 2026

Qwen 3.8 Flash-Next official released: A 6B-active open model just beat Claude Opus 4.6 Max across 8 of 9 comparable benchmarks! Qwen3.8-Flash-Next is a highly sparse MoE: • 125B model parameters • 51B additional n-gram embeddings • Only 6B parameters active per token It scores: • 62.5 SWE-bench Pro • 81.0 SWE-bench Multilingual • 73.9 CoworkBench • 55.7 JobBench • 73.5 Toolathlon • 81.3 IFBench • 91.7 GPQA Diamond • 91.9 LiveCodeBench It also outperforms Qwen3.8-27B and DeepSeek-V4-Flash across most of the table. Super cool release!!

People want to migrate from CLAUDE md so much, a blog post I wrote on it last year is still one of my most visited posts I also wrote a service that auto symlinks when Claude uses a directory that has AGENTS md. Basically seamless, automatically gitignored symlinks. I use Claude with AGENTS md and had forgotten that this problem existed Repo: github.com/osolmaz/claude-md-symlinker

Did you catch that? The new maxed out 256GB M5 Ultra Studio can be leased for *basically* the same price as a Max subscription across providers. For $257 a month, you can have on device intelligence that never runs out of tokens, and sips power. Best part is you can buy out the lease at the end of the lease for a $0 penalty. That's right 0% interest. So if the price is $12.9K and your lease is $9.9K over 36 months, then you pay the $3K difference and you now own that device. Or you can trade up into the M8 Ultra or whatever. I'm excited for this. 1.2 TB/s is pretty impressive. Can't wait to see some real benchmarks and testing on this. I'm waiting for the 512GB.