Viewing profile — abhikul0

> Most people didn't have the same kind of experience, they got the LimeWire version which was the equivalent of wading through a dollar store that’s just been ransacked and shit’s…

I tried to lookup a Star Trek episode of this premise and found a Voyager episode: https://en.wikipedia.org/wiki/Friendship_One_(Star_Trek:_Voy... This is a likely scenario of misi…

Interesting https://science.nasa.gov/mission/swift/swift-boost-mission/

https://www.logitech.com/en-us/shop/p/pop-icon-keys.920-0130...

While not exactly the hub style you mentioned, maybe this is as close to Jamming you can get. https://support.apple.com/en-us/guide/garageband-ipad/chsf2f...

Wow, didn't know about Spotify's basic-pitch or that any song to midi model existed. Gonna be a good time sink to play around with. The standalone mac app build was straightforward…

On-device video subtitles generation is exciting, should help with watching videos on mute. This seems like a low hanging fruit that should've already been grabbed by an app but I …

The blank page is what you'd get if you cleared your Watch History. I use this to watch a new-to-me topic/channel or just a video that I know I'd only watch once and don't want in …

Relevant Smarter Every Day video: https://www.youtube.com/watch?v=VPSm9gJkPxU

I'll try to use that, but llama-server has mmap on by default and the model still takes up the size of the model in RAM, not sure what's going on.

Of course the swap is there for fallback but I hate using it lol as I don't want to degrade SSD longevity.

For the 9B model, I can use the full context with Q8_0 KV. This uses around ~16GB, while still leaving a comfortable headroom. Output after I exit the llama-server command: llama_m…

Mac has unified memory, so 36GB is 36GB for everything- gpu,cpu.

A usable quant, Q5_KM imo, takes up ~26GB[0], which leaves around ~6-7GB for context and running other programs which is not much. [0] https://huggingface.co/unsloth/Qwen3.5-35B-A3…

I hope the other sizes are coming too(9B for me). Can't fit much context with this on a 36GB mac.

Have you ever tried going to the model registry and seeing that the model was recently updated? What updated? What changed? Should I re-download this 20GB file? I guess if you're n…

https://en.wikipedia.org/wiki/List_of_generic_and_genericize...

Real Science video on the slug: https://www.youtube.com/watch?v=IH_uv4h2xYM

I thought github was being wonky but yeah, getting 401 Unauthorized error. Edit: Can't view discussions as well.

And they say: https://www.youtube.com/watch?v=IfpMknlL-pg

>Scientists believe people with aphantasia use words or concepts to recall what they've seen. Like the text-encoder assisted Diffusion models?

When the app only shows posts that are more than 10 hours old even when sorting by "hot" and shoving down the algorithmic feed on the app's home page, how are people still using th…

Worked with Retiming using DC Compiler in an ASIC implementation. Remember a lot of back & forth, sometimes the tool just doesn't add enough registers to meet the constraint, had t…

The 9400 GT mattered to me as it was my first gpu. Had bought NFS Carbon only to find that the home pc only had a CD drive not DVD lol, so finally with that drive upgrade also came…