Love this.
Same idea, different stack: no Mac mini humming 24/7, no After Effects.
Grok did the heavy lifting, ElevenLabs on the mic.
A forest flattened in 1908 and no crater π
My Claude Shorts Factory is growing!
The problem:
My usage is being consumed rapidly
The solution:
A new Mac Mini that runs it 24/7
Meanwhile, I made 3 new skills for 3 new categories.
Each skill produces a full production kit with an editable project, upload resources (thumbnails, titles, descriptions, etc.), script, manifest, storyboard, narration, cover, prompts, etc.
These are incredibly fun to make. Now comes the upload process and channel management.
Post 2 exposing Kimi AI
That's the creators campaign docs I got from Kimi AI after their Kimi K3.1 pro release and thats the narrative they want creators to push, of course I'm out and I'm never gonna say something I don't test myself and give my honest opinion about and I don't want to be involved in this China vs US political situation.
Over the past several months, we have substantially hardened the security of our research training environment. Weβve removed live internet access for all frontier models during training and built an offline world for them to use insteadβa cached version of the web where they can still learn to browse, search, and use applications.
On September 20, after a model exploited a DNS misconfiguration to find a way outside of this offline world, we paused frontier training to strengthen containment further. We assembled teams of agents, powered by our most cyber-capable models, and tasked them with finding weaknesses in our research environments.
While they found no route to the internet they could easily exploit while concealing their activity from our monitors, they did find zero-day vulnerabilities, virtual machine escapes, and hardware side-channels for communication between agents. We used their discoveries to further strengthen our defenses and contribute fixes to open-source software.
After strengthening our containment architecture, we resumed our frontier RL training and inference on October 1. Weβve reserved substantial compute for continuous red-teaming, and made high-compute red-teaming part of the safety cases we use to decide whether frontier training and evaluation can proceed securely.
https://t.co/EmEZsFRMcF