rdksu
rdksu on Hacker News
Hi ! Are you guys looking for interns or smth right now , this looks like something I would want to work on xD
Bruh the harry potter theme song scared the shit out of me as it turned itself on. Bad UX for a personal site. Great article btw !
exactly how many times do you plan on posting this here
India is not an authoritarian country ffs
Hi ! This was made mostly for me to use. I didnt think much about the UX back then. Will keep it in mind. Thanks for the feedback.
This is a very exciting field to make stuff in! I also experimented with a completely client side wallpaper search xD,a while back.
In case some one is interested here is it :
https://web-inky-ten-60.vercel.app/
Hey ! Is this kind of like structured output over a large scale document corpora ?
Posted by
rdksu on Tuesday June 16, 2026 @12:06PM
from the show-hn dept.
https://web-inky-ten-60.vercel.app
I indexed around 16k+ most-viewed wallpapers from wallhaven.cc using a CLIP-based model to generate image embeddings, and then hacked together a cool demo showing the vector search working client-side using sqlite-wasm compiled with the new and upcoming sqlite-vec extension, which allows me to do the vector search over the image index client-side! The inference over the actual text-encoder of...
This is so cool! Could you add a feature to export my tree as an svg please? Would love to put it on my git profile !
The article is so opaque in arriving at its conclusion; no prompts are disclosed, and nothing about the said simulation. What is stopping me from believing that you just put 'mandatory usage of nukes' in your system prompt?
The only bit AI can't replace is probably the need for a 'fall guy' or someone to take responsibility for something. This, however, will obviously not be sufficient to prevent job losses.
Only if they could mass produce flux capacitor.
I made a semantic search-based wallpaper setter by indexing a couple of 1000 thumbnails off wallhaven :)
I have updated the popular /grill-me skill for this exact purpose! I had a very insightful grilling session yesterday on what exactly happens when you try to load an extremely large dataset in pandas, covering everything down to the last detail !
Google also released colab-cli a couple of days back and its pretty good at functioning as an isolated sandbox for running random python scriptS .
Have you run ablations on the actual effect/impact of on-policy distillation on contributing to the performance ? Just Curious ! As Unsloth based mixed quantisation methods on MoE models are widely used with great community rep.
I find takes like this weird for the primary economic conundrum of 'who' exactly will this increased productivity be for , to produce what , to render what service , when everyone is out of their jobs ?