Viewing profile — Yukonv

Needs a big asterisk on “stores it forever in the cloud.” That information is end-to-end encrypted and not accessible to Signal or anyone else. If you don’t want that feature you c…

Signal is private with a phone number for the purpose it serves. Its does not aim to be an anonymous chat service. For 99% of people Signal is ideal for private communication and w…

What models and quantizations have you been trying? I've had great success with the larger Qwen 3.x models at 6-bit levels. Using 6 bit quantization is really the bare minimum to g…

Have been using Qwen 3.6 27b recently along with various other models the last month and it is very capable for writing code at a level I haven't need to use a subscription for 95%…

Some broad assumptions are being made that plans give you a precise equivalent to API cost. This is not the case with reverse engineering plan usage showing cached input is free [0…

It is possible but requires a very specific model design to utilize. As this reverse engineering effort has shown [0] "The ANE is not a GPU. It’s not a CPU. It’s a graph execution …

Unsloth quantizations are available on release as well. [0] The IQ4_XS is a massive 361 GB with the 754B parameters. This is definitely a model your average local LLM enthusiast is…

With that you are taking a significant performance penalty and become severely I/O bottlenecked. I've been able to stream Qwen3.5-397B-A17B from my M5 Max (12 GB/s SSD Read) using …

The latest release v0.3.2 has partial support, generation is supported but not all special tokens are handled. I've done some personal testing to add tool calling and thinking supp…

The model does have the format specified but there is no _one_ standard. For this model it’s defined in the [ tokenizer_config.json [0]. As for llama.cpp they seem to be using a mo…

Good to see Ollama is catching up with the times for inference on Mac. MLX powered inference makes a big difference, especially on M5 as their graphs point out. What really has bee…

That’s exactly what I thought about. Getting my hands on an M5 Max this week and going to see hows Dan’s experiment performs with faster I/O. Also going to experiment with running …

Another good option I’ve personally used if you want a smaller API surface with just Result and Maybe concepts is True Myth. https://true-myth.github.io/true-myth-csharp/

Related, Intel was showing off Thunderbolt Share at CES[1]. Allows Thunderbolt 4/5 device-to-device transfer of files. Theoretical speeds in the 20Gbps and 40Gbps for Thunderbolt f…

Great find! Seems to be a common issue with games, found the same issue with trying to auto play PICO-8 cartrages on web.

Edit: Keyboard input does not work :/ it was a good effort. Found a workaround throw it in an iFrame and have the frame load with a user interaction. Here is a jsFiddle link, just …

Firefox prevents audio from playing with no initial user interaction like a play button. Can see the warning if you pop open the dev console. Don't know of workaround besides sites…

Little late but though I would say hi. I too got started programming thanks to Minecraft. My first real job was working at Overcast Network (oc.tc). I remember having to scale out …