Holy Crap 🤯 Local AI is getting dangerously useful.

👀 I ran Qwen 3.8 27B locally inside Hermes Desktop and gave it two real jobs: 📄 Process messy bank statement PDFs 🛠️ Call tools using Hyperframes No cloud. My files stay on my machine. Local LLMs aren’t just chatbots

Prince does AISep 1912

Alibaba just quietly dropped a model that watches video the way you do.

Not a transcript. Not screenshots. The actual footage — sound and picture, together. Here's why that's a bigger deal than it sounds: → Most AI reads text or looks at one image at a time. → Qwen 3.8

Julian Goldie SEOSep 19

Contrary to the previous example

Contrary to the previous example, this is an example of a failed prototype where I tried using Jev but it was not effective and ended up costing me more. If you combine Jev and Groq, wouldn't it be super fast? I tried that, but as a result, Groq alone was sufficient, but the cost jumped 20 times...sweat…

niwacisSep 191

Here’s my first test of Qwen 3.8 27B on the inco_ai Splash inference engine.

✅ More than doubled the tokens/s that the M5 Pro was getting on oMLX. ✅ Two command setup ✅ Equal Game/Code quality

MechanistixSep 193