Viewing profile — anax32

With new tools (i.e., LLMs) it feels like software engineering is moving to an assembly process. The best engineers will have an awareness of overall problem, architecture, how pie…

yes, that's what I thought. "You got a loicense for that PSU?" is my biggest fear!

A ban on desktop PC components over a certain power threshold (300W) or PSUs would definitely affect local AI, and Europe is not a big enough market, nor has it's own internal supp…

And it is focussed on social networks, which require an email address, which usually implies a device. But instead of inserting controls around email addresses (as with paid servic…

The US "product machine" is so strong. They really know how to do frictionless signup and vendor lock-in on the corporate side.

Can anyone explain how this ultrasound can see through the skull? I've worked on ultrasound devices and data, the shadows from bone, and distortions caused by tissue types were ver…

Yes, thank you. That's exactly where I am, and trying to gather some knowledge. The power draw from the wall is especially important, because a spike across multiple devices at the…

How do people measure power usage of GPUs at large (32x) self-hosted setups or small multi-rack setups? I've seen some PDUs which collect and transmit data, but I'm unsure of the p…

Open weight and local hosting is far, far cheaper. In every respect. Even support is cheaper, over time. However, it's difficult to sell this to businesses who want contracts and K…

I've just made a milestone on my project, moving away from AWS (budget) to self-hosted and the local models are so much faster than in the past. Beyond LLMs, having embeddings, ima…

I'm not getting any work done today thank you!

* You will have logs Always gets me

This was a big moment for me, but I now believe it's fictional. Thanks Ballard

This stuff is better than TV

HTTP content negotiation was a good idea which decouples content from form, but only as far as format selection. Generative models are able to transform content between media types…

I've been thinking of LLM prompting as execution, which makes context building a compile step -- different build systems, different output quality. Chunking is the simplest compile…

[dead]