Cool! I made something similar with the same datasets a year ago, but with geocoordinates instead of timestamps: https://theilemail.de/wikipage/ It shows a zoomable map with the "most important" wikipedia entries at specific locations.
It was very hard to get the parameters right so that the text is always displayed in a good size, while showing not too few or too many entries. I never published it until now, I think.
No, it is not as good as Veo, but better than Grok, I would say. Definitely better than what was available 2 years ago. And it is only a 7B research model!
Yes, of course I do ignore a lot in that calculation. I just wanted to calculate the biggest possible usefulness of this cable. Especially the resistance losses could be quite disastrous.
If I (and only I) owned such a cable from Europe to the US, how much money could I make by buying cheap solar energy from the bright side and selling it to the dark side of the Atlantic?
First thought:
10 GW * $0.03/kWh 4 hours/day = $1.2Mio per day [0]
I wonder if you could implement it with only static hosting?
We would need to split the index into a lot of smaller files that can be practically downloaded by browsers, maybe 20 MB each.
The user types in a search query, the browser hashes the query and downloads the corresponding index file which contains only results for that hashed query. Then the browser sifts quickly through that file and gives you the result.
Hosting this would be cheap, but the main barriers remain..
Very cool open release. Impressive that a 27b model can be as good as the much bigger state of the art models (according to their table of Chatbot Arena, tied with O1-preview and above Sonnet 3.7).
But the example image shows that this model still makes dumb errors or has a poor common sense although it read every information correctly.
I made a similar map but with tiles that only load of you zoom in far enough: tomthe.github.io/hackmap/
(Sorry for posting my link so often)
That way it has to load only a few megabyte for the first view.
Nice introduction, but I think that ranking the models purely by their input token limits is not a useful exercise. Looking at the MTEB leaderboard is better (although a lot of the models are probably overfitting to their test set).
This is a good time to chill for my visualization of 5 Millionembeddings of HN posts, users and comments: https://tomthe.github.io/hackmap/
This one might be interesting for you: https://daylightcomputer.com/
it has a fast e-ink-type of display. Unfortunately it is expensive and not available.