As I understand it, it records when you're writing, including all edits and such, and verifies it's human based on that. Well, see the demo at https://inktrail.co/in-action
It will probably work well right now, but I don't know how easy that would be to fool once the hucksters build tools to circumvent it.
Wut? The causation can flow the other way as well. Having high tike preference results in lower household income. And time preference is probably genetic. They literally controlled for the variable they were testing for....
- TalkToYoutuber[1]: Download the transcripts from a youtube channel and hook it up to gtp4 with RAG to let me "talk" to youtubers. There's a bunch of youtubers who have useful knowledge to share, but no blog or wiki, so semantic searching their video transcripts is the next best thing.
- YoutubeThumbnailSearch[2] - Embded all of a youtube channels thumbnails using CLIP and search them using text. I often need to search through news channels with 10k+ videos, often in foreign languages, so not having to rely on the title or transcript but the video thumbnail helps. This is a much more niche usecase tbf.
I am thinking of making a scaled down version of [1] so I can "talk" to long videos, like conference speeches or university lectures. Should take an hour or two to cook it up since it will reuse most of the code from [1].
Something like talktoyoutuber would also be very useful for certain discord servers. They'll have a lot of knowledge on something but will gatekeep it with "just use the search." and they'll refuse to build a wiki or really engage in any kind of organization.
I can cook it up if it would actually get some users.
Ultimately, I want to make a tool where you can plug in any arbitrary document store/scraper to an LLM with RAG. But I think we are still not there yet in terms of all purpose scrapers.
> I am thinking of making a scaled down version of [1] so I can "talk" to long videos, like conference speeches or university lectures. Should take an hour or two to cook it up since it will reuse most of the code from [1].
This would be useful to me as well. If you do end up making it, could you reference it on your existingGithub
The projects are dead simple. I think if Youtube wanted to, the would have implemented this long back. It's probably a legal landmine and financial tar pit. But thanks nevertheless.
You’d be shocked at how hard it is to fund, start, and ship even a basic project at a company the size of YT or anything else in the Google/Alphabetaverse. It’s probably also a legal landmine and all that, but organizational friction’s more than sufficient to explain simple useful features failing to ship.
Don't forget how Google incentivizes projects, one gets promoted for shipping the project, not for maintaining it. If indeed this were shipped at YouTube, I wouldn't be surprised if it gets slowly deprecated or outright shuttered in a few years. It's better to keep it open source for everyone.
This is overly simplistic thinking. Of Course increases in technology isn't the only factor determining aggregate societal well being or happiness or whatever. But it would be naive and disingenuous to suggest anything other than it being monotonic at the very least.
This also asks for a search for better social technology, as opposed to asserting that we must slow down the search for better physical technology because the social technology isn't keeping up.
This is tortured reasoning. Or worse, deliberately misleading phrasing on your part.
Let's say that some unspecified statistical technique found two distinct clusters from some given raw data. These two clusters almost exactly line up with another set of clusters, and the reason for that another set of clustering is Z.
Implying that the first set isn't because of Z but it's probably all a confounder is... technically true, but extremely misleading for just about any and all sensemaking that we do.
If we applied this level of epistemic caution to anything at all, we would never pull conclusions about anything ever.
---------------
I'll say the quite part out loud. Blank slatists and their political ilk are not this careful about statistical inferences when it aligns with their preconceptions.
Everytime I read one of these "how to hire" posts, it's always a opinionated clusterfuck of a process that is arbitrary/capricious, gameable and biased towards what OP thinks are good traits.
This is a problem that is very easy to solve if you were allowed to use proxies for intelligence and grit. Just test for IQ and trait conscientiousness. [1]
GDP always gets trotted out as if it is a holy grail and a benchmark for social welfare, which it isn't so think of it as a (failed) preemptive strike against getting a longer comment thread.
