Generative models, prompting, agents and AI tool capabilities.
I Tried Coding with Local AI Models for 7 Days
23d ago · English audio
I wanted to try I coding with only local AI models like Qwen, Muse, and OpenAI OSS for a whole week to see how they perform. The results were interesting. To run local AI models I tested with the latest hardware from ASUS, the NUC Mini Pro PC: https://www.asus.com/au/displays-desktops/nucs/nuc-mini-pcs/asus-nuc-16-pro/ Lots of benchmarks tell you that models like Qwen 3.8 are at the frontier giving results similar…
Adrian Twarog
I'm Adrian from Australia, a web designer and developer who makes websites and apps using AI platforms like Claude, OpenAI Codex and Gemini. I'm building startups that use AI generation and #ai #programming #ui #ux #webdevelopment #development #code #webdesign #openai #claude #openclaw
Outlier score
This score was measured on Sun, 25 Oct 2026 07:40:49 GMT. Current view counts may differ.
91K views ÷ a 20.5K baseline = 4.4×. Compared with 16 earlier videos from the same channel, matching the format recorded at scoring time. Older-upload baseline: reference videos had at least as long to gain views. This comparison is not age-matched.
YouTube snapshot: Sun, 25 Oct 2026 11:05:14 GMT. Counters may have changed.
Read the methodologyGenerative AI & Agents
Channel-balanced percentile: 82
Comparison details
50 videos from 29 other channels, with each channel weighted equally. Same format and language, with 100,000–999,999 subscribers. Observed at 559 hours after publication, within ±48 hours.
This describes the collected sample, not all of YouTube. Updated Sun, 25 Oct 2026 11:07:11 GMT.
Niches & tags
Transcripts and detailed analytics are available for recent outlier Shorts up to three minutes. Research tools