Viewing profile — andhuman

I don’t see why they just don’t allow a smaller model to answer the question while letting the bigger one vet it. The vetting can be asynchronous and can be delivered after a few s…

What surprised me is that caffeine gets converted to other compounds that _also_ binds to the same receptors thus causing you to feel less tired. And that compound has its own half…

Why conscious thought as described in the article was thought to be signs of a delirious person was because that’s where you could find it in real life, is my guess. If someone bla…

Finally an alternative to the big dogs that a company can use. People have been asking for a way to run the Chinese models from a trusted provider. Here GitHub delivered! The perfo…

The Vibe CLI is really bad on Windows, sure they don’t officially support it, so can’t blame them, but a FYI for anyone wanting to try it. It can’t get find and replace right.

I have good experience with Mistral Vibe.

I just listened to the Matrix OST and that one really gets me into a coding mood!

Oh man, this was the release I wanted to link, as it has a new feature (tiled follow link) that I actually started using right away. A new browser feature I find useful didn’t happ…

Be kind to others, but start with being kind to yourself.

Isn’t llama.cpp’s implementation of Qwen 3.5 better, or am I misinformed?

What helped me get a better understanding of oauth and oidc, was this YouTube video [0]. [0]: https://youtu.be/996OiexHze0

Same setup I’m using! Parakeet and pocket turbo. It’s feels good enough for daily usage.

Have you tired using the run action instead to clean the data? Win+r

I have this nagging feeling I’m more and more skimming text, not just what the LLMs output, but all type of texts. I’m afraid people will get too lazy to read, when the LLM is almo…

One of the more annoying software that does this is the copilot Office 365 on the web. Every time (!) I open it, it shows a popup on how to add files to the context. That itself wo…

I built this recently. I used nvidia parakeet as STT, open wake word as the wake word detection, mistral ministral 14b as LLM and pocket tts for tts. Fits snugly in my 16 gb VRAM. …

It’s uncanny good. I prefer it to pocket, but then again pocket is much smaller and for realtime streaming.

Gave it four of my vibe questions around general knowledge and it didn’t do great. Maybe expected with a model as small as this one. Once support in llama.cpp is out I will take it…

I’ve tried the voice clinking and it works great. I added a 9s clip and it captured the speaker pretty well. But don’t do the fake mistake I did and use a hf token that doesn’t hav…

I’ve recently bought the LG with 4th generation OLED, and for me that works for long coding sessions (I use it for work). They shifted or did something with the pixel arrangement f…

Interesting experiment. I would hazard to guess that Google is on top when it comes to these sorts of things (spatial ability), then OpenAI and last Anthropic. I would like to see …

The new LG panels are bright enough. I think they’re called 4th generation WOLED.

This is big. The first really big open weights model that understands images.