Good for them! Milk that job for all its worth!

Yeah but it works and it’s still free 🤷

It ain’t much, but it’s dishonest work.

The AI features are actually pretty cool!

Using a local AI model (running on your own GPU), you can:

• Drag files on to the “AI bar” to bring them into the context of a prompt.
• Tell it to perform actions like, “merge these two PDF files.”
• Use it to search your filesystem, “find pictures of spiders.”
• Ask it to find system settings or tell it to change them, “turn on dark mode.”

It supports voice and probably visual (e.g. with a webcam) I think.

Best of all: It doesn’t send any of that to some data center in the cloud! I mean, you can configure it to do that but you can just as easily use say, qwen3.5.

Note: It’s not realistic to expect to be able to use local models if you have less than 16GB of VRAM (in your GPU). I mean, some 8-billion parameter model will work with say, 8GB but you’re not going to be satisfied with the results most of the time 🤷

No one will believe you, so they’ll call it “sock therapy.”

For a wifi option, you can use Droidcam with OBS. Setup the virtual camera inside OBS and you’ve got a wifi webcam that you can walk around with.

I’ve used that setup many times and it’s sweet. At work my coworkers are all astonished and amazed when I use the OBS virtual camera pass-through to my virtual desktop to walk around while talking (I use a wireless headset for the audio). I can even show various overlays of my desktop with my face and a downcam I have setup for demonstrations (like a craft cam setup).

Combine it with RVC voice changing silliness and they’re all blown away. The security folks (of which I’m a part, haha) always freak out a little bit when they see me share my Linux desktop when I’m on Teams via the company’s virtual desktop. “That shouldn’t be possible!” Haha

I don’t have the heart to show them how you can copy and paste huge amounts of text into the virtual desktop directly (clipboard sharing is disabled and prohibited 🤣).