Viewing profile — twayt

This is actually pretty useful

Also checkout www.askYouTube.ai Which does essentially this but requires no indexing of videos!

Yea I think this is the most reasonable take. You can always check information before believing or acting on it. However it’s often super difficult to even get started and know wha…

This description is wrong on so many levels. Amphetamine is primarily absorbed through the plasma membranes and not DAT since it’s lipid soluble. Dopamine does not and thus relies …

You get the same result in a short span of time, heck you may even get a reliable error bound. Where this falls apart is that error accumulates over time and not just for one heap …

We need to bring back Kazaa

[flagged]

Also try www.askYouTube.ai for q&a across multiple videos!

Its fixed now unfortunately the email you provided on the contact form bounces.

Despite the rude comments you left on my contact form, I have noted your point and am making changes to fix this.

Also try www.askYouTube.ai, not exactly pure text search but it can help you find videos that answer your query using LLMs

Thinly veiled attempt to advertise bentoml, their startup. You can just use huggingface and Automatic111 for this, not sure why this is needed at all.

Did you just completely ignore the basis of my comment and instead specifically respond to what I explicitly explained was not the point I was making?

I find your statement about the Edison quote disingenuous. I did some reading about the origin of the quote and it isn’t as cut and dry as you seem to claim. Also, the quote is mea…

Installed it, can't even get through the tedious intro and stuff

People have a visceral reaction to the image of them being in a self driving car and hurtling to their death with no control. What they don’t have a visceral reaction is to be save…

Until you get models with completely disentangled feature spaces such that you know that the influence of a piece of data is completely removed (at the limit this is something like…

> They probably can: No, actually they probably can’t. There is no verifiable way to remove the data from the model apart from completely removing all instances of information from…

If you recite enough small snippets, you make a large one. Especially with ChatGPT you can probe the model by asking certain questions about the material at hand to see if it has s…

Libgen / Scihub or not, if the model can provide details about the book other than just high level info like the summary and no explicit deal with the publisher has been made, you …

Sounds like an FB shill

Yea you can create the nicest office of all time, still wouldn't want to live there or trade it for my own private personal space. Way happier to work hard and contribute to the co…