Fun trivia for a friday night!
Which of these pages was built by Claude Code and which by a local model (Qwen 3.8) running on a custom agent harness (Pi)? Same prompt, no skills, no additional context.
Hooked up DeepSeek Harness to my Even G2 😎 Fully local setup
Uncensored Qwen 3.8 on my desktop，MLX Whisper for STT on my Mac.
Atomic Chat rented a single RTX 6000, booted Qwen3.8-27B, and posted benchmarks on four tasks
A music library as JSON, a Python rate limiter, a seating puzzle, and a heist story. The media thought that was the story. It was not. Behind the bench test: DFlash2 looks at the
I had some fun playing around with the Qwen 3.8 model yesterday.
What blows my mind is that it's nearly a frontier model yet it runs on my 5 year M1 Max laptop! Now it's not super fast, 16 tokens/s but still! Check out the little video I made about how to set it up:
You have reached the end of the archive
All of qwen38