Qwen 3.8 27b surprises again.
I recently found an interesting video on X that showcased the capabilities of p5.js. I decided to try building something different, but using a local Qwen 3.8 27b. After an hour of tweaking, the result was unsatisfactory. Each iteration was
Sui tested opus 5 against fable 5 on 3D generation
Ran the comparison nobody at Anthropic would publish on launch day: same 3D prompt, both models, judged purely on final texture and detail quality - not speed, not attempt count scoreboard everyone will screenshot: Called
Claude Opus 5 vs GPT-5.6 Terra for computer use.
Open in Chrome and create a bold poster titled RAINBOW VENDING MACHINE. Draw one large purple… Claude Opus 5 won against GPT-5.6 Terra. Go try computer-use agents for free at
This is Claude Opus 5 writing 469 messages in MY turn.
I wrote none of them. Mobile, voice mode. No compaction, short session. The scroll doesn't end.
You have reached the end of the archive
All of Claude Opus 5