Rendered at 13:25:36 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
8s2ngy 19 hours ago [-]
I was thinking of doing something like this myself. I've been pondering how to use AI to support, rather than subordinate, human work. Instead of using AI-generated artworks for blog posts and press releases, it would be better to use AI to "intelligently" search across humanity's collective oeuvre and find artwork relevant to the accompanying text. Once the AI hype dies down a little, it would be worth thinking about how we can highlight or enhance human creativity instead of downright replacing it.
cj00 21 hours ago [-]
I used the same concept to build a searchable database of YouTube thumbnails in my watch history. I always end up trying to remember a video I didn't finish from a week or two ago and YouTube's history search plain sucks. So I built an app that tracks all my watch history across all devices, downloads the thumbnails and runs them through a local Gemma model to write a paragraph description and OCR any text in the thumbnail.
Currently at 30,000 thumbnails described, basically 2 years of watch history. Search is via FTS5 in SQLite and works great on an 8 year old MacBook Pro.
akutlay 4 minutes ago [-]
Does a thumbnail have enough information to support your search? I’m curious because i would think you need the full transcript of the video for something like this.
order-matters 21 hours ago [-]
what kind of storage impact do you have?
cj00 21 hours ago [-]
Currently at 3.8 GB for the YouTube thumbnails. An additional 800 MB for Crunchyroll thumbnails.
Symbiote 21 hours ago [-]
https://www.europeana.eu/en indexes 60 million museum objects in Europe, although that includes objects that aren't artworks.
(I suspect The Last Museum is using the same open data exports.)
Search would need some improvement. Nevertheless, it is cool to have all art pieces available in one place. Bookmarked.
timdiggerm 19 hours ago [-]
The title assumes that the point of a museum is simple being able to see the work; it ignores the interpretive benefits of a curated exhibit.
billbrown 13 hours ago [-]
"Access" is the main point, not the sole point.
floathub 16 hours ago [-]
So much is missing (e.g. "Group of Seven" yields nonsensical results). Nice idea, but probably needs a couple of orders of comprehensiveness to be anything close to justifying it's name :-)
mcmcmc 23 hours ago [-]
Incredibly off-putting name for a search tool
whyage 16 hours ago [-]
Only someone who has never been to an actual museum can call this thing a museum, let alone the "last one."
thmoonbus 22 hours ago [-]
I agree. When did we, the tech set, become so arrogant?
mcmcmc 22 hours ago [-]
We? There is no monolith here, this is individual arrogance from people who believe AI is driving us to the end of history
Projectiboga 20 hours ago [-]
Could just be the first catchy short-enough url they could find.
BugsJustFindMe 20 hours ago [-]
I tried searching for "holofernes" and got many paintings not-of-but-aesthetically-similar-to Judith beheading Holofernes. I then typed directly "judith and holofernes" and got similarly undesired results. I know that I'm "holding it wrong" here, but this might not be the last museum after all.
phainopepla2 20 hours ago [-]
Yes, it would probably benefit from a hybrid search with RRF.
scanny 22 hours ago [-]
Would make sense to have a copywrite filter so you can specify to see only public domain images.
This is cool, but I agree name is weird. Kind of wonder if the timeline should be logarithmic because I would assume the distribution of art over the years is far from uniform.
traceroute66 23 hours ago [-]
Interesting concept. Its desperately missing a decent filter function though.
Just dumping a million results on the user to doom-scroll through is a bit problematic in terms of UI/UX.
whilenot-dev 22 hours ago [-]
There's nothing between 1975-2026?
EDIT: Ok, there is, but it needs a query...
raylad 21 hours ago [-]
Completely failed if you search by Artist name
bbor 19 hours ago [-]
Very cool. If the author's here: is this using the new EmbeddingGemma2, presumably? It's been absolutely blowing my mind.
soviets were big into seals and govt procedures . maybe?
MitPitt 23 hours ago [-]
This website likely uses a semantic vector space like CLIP or BERT space. Which is based on co-occurrence of words, it doesn't have a harder logic behind it. Soviets probably had cylinders in some machinery which is why it pulled.
dominotw 21 hours ago [-]
can you help me, how is your comment different than what i said?
how do you know its 'cylinders' and not 'govt seals and procedures' ?
billbrown 13 hours ago [-]
Maybe try something more semantically meaningful? "Soviet realism" looks pretty good (no seals):
Curious whether the embeddings come off the images or the catalog text, because in my experience museum metadata is wildly uneven (half the Met's older records are basically "Vase, terracotta"). Also, do you dedupe across institutions?
phainopepla2 20 hours ago [-]
Based on my search attempts for specific works or artists by name, it seems that it's not using the catalog text.
Currently at 30,000 thumbnails described, basically 2 years of watch history. Search is via FTS5 in SQLite and works great on an 8 year old MacBook Pro.
(I suspect The Last Museum is using the same open data exports.)
https://lastmuseum.com/search?q=art%20deco
Search would need some improvement. Nevertheless, it is cool to have all art pieces available in one place. Bookmarked.
Just dumping a million results on the user to doom-scroll through is a bit problematic in terms of UI/UX.
EDIT: Ok, there is, but it needs a query...
soviets were big into seals and govt procedures . maybe?
how do you know its 'cylinders' and not 'govt seals and procedures' ?
https://lastmuseum.com/search?q=soviet+realism