Viewing profile — dr_kiszonka

Why are we regurgitating the past? How did it even make it to the home page? (And why is this the top comment?!)

I find video models very hard to steer. They can output amazing "shiny" things quickly, but if you want something very specific, you may need to spend days on it. It is not like si…

> the point of learning should not be to do something, but to expand your own mind and understanding of the world (and beyond) I agree with your comment overall, but people have di…

"An increased risk of Guillain-Barré syndrome (severe muscle weakness) was observed after vaccination with SHINGRIX" https://www.shingrix.com/side-effects/

I get that people see this and think: ads and social media. My first thought was cognitive neurorehabilitation and brain stimulation. Realistically, probably ads, but maybe not onl…

Cooperative Thread Array

Only if you have a wide enough screen. I had to rotate my phone to landscape. Thanks for the pointer!

I agree with you. But do you remember when we could chat with a colleague about how much of a doofus our boss was without worrying that some automated system would possibly notify …

Also, a bit like emacs.

Maybe it only occurs in certain browsers? It does in my Chrome for Android [...]

Qwen is a really good name.

Maybe with very fast models you could request animation frames, e.g., frame 1) right foot at 12, left foot at 6; frame 2) right foot at 3, left foot at 9, etc.? And instead of repo…

Does Mouseless support multiple monitors? I have been trying out similar software for a few years but haven't seen one that would let me "click" outside the main monitor on Windows…

When would a larger model have a smaller inference footprint? If the larger was MoE and the smaller was dense?

This is great! I haven't heard of gmailctl before.

> than a structured collection of md files. I think it depends on what a memory system includes. Those that automatically inject relevant information into context are in my experie…

It isn't ideal, but I am starting to write code (with AI tab completions) while waiting for LLMs. The tab completions are sometimes overeager and I wish I had more control over the…

Thank you for explaining. Do you think there are still opportunities for stack optimizations to meaningfully speed up inference on single consumer-grade GPUs?

I am lost. Codex can't look up stuff for you in your codebase? GitHub Copilot can't look up PRs for you?

For Codex, that is ChatGPT? https://openai.com/index/work-with-codex-from-anywhere/ Or do you want it to speak to you too? I think this would have to be TTS on your phone. You can …

Very nice! Would you have any recommendations for the leanest compatible "host"? Instead of adding this to my VSCode, I would rather use it as a separate app. Currently, I use a na…