VideoZero to MVP (Nick Blokhin) · Oct 19, 2026
Can an Agent Make a Small Local Model Reliable?
Same local model, same GPU, same tasks, two different agents. In one, Qwen 3.8 27B made zero mistakes across nine runs. In the other, it got the numbers wrong twice and confidently reported that…
More to watch
Zero to MVP (Nick Blokhin) · Oct 27, 2026
$7 vs $0.65: Opus 5.5 and MiniMax M3.1 Flash on My Go Project
Comparisons & reviews · Cost & limits
Zero to MVP (Nick Blokhin) · Oct 24, 2026
Kimi K3.1 Pro Is Nearly Opus 5.5 on Paper. What About a Real Project?
Comparisons & reviews
Zero to MVP (Nick Blokhin) · Oct 18, 2026
New DeepSeek V4.1 Flash vs Claude Opus 5.5 on a 20,000-Line Project
Comparisons & reviews
The Gray Cat · Oct 27, 2026
OpenCode Go + CodeGraph: Can Cheap Models Do the Job?
Open harnesses · Cost & limits
The PrimeTime (ThePrimeagen) · Oct 24, 2026
OpenCode got hacked
Open harnesses · Security & sandboxes
Leon van Zyl · Oct 24, 2026
Unplug the Internet: Free AI Coding with Ollama
Open harnesses · Cost & limits