sirpilade

I’ve been thinking for a while that these tools should be slower. This doesn’t mean lower quality, they could still think (ah wait, overthink) at same speed. I’d just like them to output text at the same speed I can read and understand. This would make it more like a conversation, where you hear the flow of concepts coming and at the same time think about it and get involved in the conversation. For some reason I enjoy more running a local LLM at 4 t/s than a faster than thought change to my whole codebase by Opus

Aeneid, it’s been a while since my school years

Is there anything similar for sharing cuda computing capabilities?

IMHO, it's dependability. It's easy and flexible because I can set it up as a web service or use it offline. For the average reader of HN, it takes probably 10 min to set it as web service with npm and reverse proxy + SSL and then you can use it from any device. With a little CSS it can be beautiful and with plugins you can have a connection graph similar to Obisidian. Once it runs, then I don't need to worry about updating it every other hour because of bug fixes and compatibility breaks. And I know it will be there for the next 20+ years.

As a more general comment, I hope we’ll stop trying to discriminate whether a certain text was or not written/polished/extended by AI and focus more on content and author’s responsibility for what they do or do not say with that text.

I think that having the « How it works » section in the README makes the aim of the project a lot easier to understand

Pun aside, I cannot fully trust a centralized URL checker on a remote server that I don’t own, even if they guarantee that my privacy is safe

But hits 100% of browsing tracking

Yes, but it’s not flipped

Is anybody using any open source, self-hosted solution with an UI on par to whatsapp? Asking for my wife