TechSquidTV

It's also extremely gross to steal.

It is pay walled. You actively subvert it.

it is. yes

The contract (TOS) of you watching my content, is you pay. You may pay in ads, or you may not watch. Anything else is theft.

Fundamentally against stealing from creators.

I would have assumed plan modes make use of tools to keep the goal/plan persistent across compaction etc. Is that not the case?

This really only inconveniences people, not bots.

Woah believe it or not, that's Numberwang!

Hey all, This is my project. Started about 6 months ago and have been working on this last update for roughly the last 3 months.

Cliparr is a video clipper for Plex, Jellyfin, and local video. It's a video editor, but its only job is to export a clip from a video. For things like gifs mostly.

When I went to add subtitle tracks to the editor, it bogged down like crazy. So, probably bigger than Cliparr is the new underlying library for the timeline editor. You can read more about that in the post.

Hope you enjoy!

Almost like the algorithm is listening.

I have been getting into this as well. I had ChatGPT plan up a new UART adapter and similar.

... So we both agree.

It still helps deduplicate.

LLMs are static though.

It's not a bad market to aim for. No one else really is.

Is it doing any circuit simulation or anything?

This is what I want to know as well. I'm about to kick off a project or two.

They do have that. All archives have torrents.

I thought development officially ended?

It's incredibly poor performance, unfortunately.

Incoming vandalism because of stolen jobs or something.

I attempted their chat demo to see the speed and it stated the model couldnt be found.

edit: Tried signing up and using the internal playground. Holy shit thats fast.

They were not. Apple refused to acknowledge what they had.

I had tried (and failed) to do something similar. https://analogui.com/

Dear God, I hope he transferred that knowledge the best he could.

In my limited experience, not quite yet but we are damn close. Qwen 3.8 27b is it. If I could run this as a decent speed, I would no longer need cloud models at all. I'm actually currently trying it out in the cloud to pay for the inference speed but the model is fully runnable at home.

I realistically costs $5-10k to replicate a ChatGPT like agent. And it doesn't scale.

That's still really close. And models and quantization etc keep improving.

I'm absolutely positive that I'll be switching to mostly local AI in the next 5 years.

I only with I got more than 96GB at the time.

I'll share, Codex does not give a single fuck about piracy. Go nuts. Setup a fully automated arr stack with a seedbox.

Gemini by comparison will not help you find archives of old magnet links because they COULD be used for piracy.

7 million would sound fair to me. 7 billion? Explain yourself.

Ironically I had just installed omlx, tried 3.8 27b 8bit and then Googled about it overthinking, then this was the first result. 4 hours old.

This still requires 128Gb of memory, right? Me and my lowly 96Gb, like a commoner; missing out on the fun.