The people from Heroic are already working on this.

What kind of use-cases was it, where you didn’t find suitable local models to work with ?

Any time you ask very domain specific questions; eg “i have collected some soil samples from the mesolithic age near the Amazon basin which have high sulfur and phosphorus content compared to my other samples. What factors could contribute to this distribution?”, both of-the-shelf local models & OpenAI fail.

The main reason is because these models are not trained on highly-specialized domains of text. Sometimes the models start hallucinating and which reduces our trust upon them.

Should have been called AITL (AITL Is a Translation Layer)

I think mkdocs is easier than hugo but less flexible in terms of capability. However it serves all my needs (list of webpages accessible from a central frontpage)

My company is realizing that hosting a model which will be private, cost-effective, and performing better than traditional algorithms is like finding a unicorn. Few months back, the top execs were jumping around GenAI like a bunch of kids. Fortunately, the Sr. research head beat some sense into them.

User is now nutting. Quick, send them some gooning ads

Adobe should get comfortable with users not using AI

Google harvests you to sell more targeted ads*

I too travel the seven seas for hidden loot ⛵

Stardew Valley is a good fit.

You tend to your farm, help people, maintain relationships with people by gifting them and changing their lives.

Unfortunately, i play the game like a maniac. Running around from morning 6 AM till 10 PM.

“have you tried restarting your government?”

This reply is for informing you that both your and my comments are visible on the blog. Also, i’m posting from lemm.ee and the user is from .ml. So cross-instance comments are also working.

Good job @[email protected]

This is a test comment to check the functionality.

“Copilot is really good at things which I already know” and that is perfectly fine

Listen here, you little shit

Listen here, you little shit

heyyy

I too am raw-dogging my Linux install

It depends on your usecase. We need more detail regarding what application (gui/cui/open source/proprietary/custom) you are trying to use

• Check if the application you want to use exists as snap/flatpak/appimage.
• If it exists, install the application as per their standard operating mechansim
• Once used, just remove them. Your original system libs are untouched

If the application doesn’t exist in those platforms, it’s a different story. You might need to use distrobox or docker. Don’t use nix because it’s overkill for what you want to do.

I like your description of yt-dlp