I ran the same task on Claude Code and DeepSeek's new agent harness.
One cost $150. The other cost $2. Today we're launching (agentsky_dev), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in
I plugged Qwen 3.8 27b into DeepSeek Harness and asked for a replica Age of Empires 2
Returned to my Studio 70 minutes later to find the Mac still purring... So far my local model tests on this prompt have produced unsharable results Let's see what we get
DeepSeek Harness. Hands down the standout, and honestly not what we expected going in.
The final page had a level of polish we didn't see coming. It also took its time — this one clearly likes to think before it builds, and it ran way longer than Pi. Results:
We tested Ox Alpha in Pi and DeepSeek Harness.
Same task for both: use ego lite to scope out a few great sites, then build the most impressive single-file HTML landing page. The gap was bigger than we expected 👇
You have reached the end of the archive
All of deepseek