software mechanic

segfault
Joined August 2023
supermercat retweeted
LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.
42
125
47
846
171,866
supermercat retweeted
pip install -U mlx
8
25
2
188
14,141
supermercat retweeted
🎵🎶♥️ Shobii ♥️🎶🎵
2
11
1
83
4,307
sugoiiiiiiiii
visionOS 2.1/MLX: Llama 3.2 1B in 4bit on AVP🌙 - clone mlx-swift-examples - add Llama 3.2 model configuration and run on AVP - visionOS 2.1 beta 2 / Xcode 16.1 beta 2
1
2
196
SHIEEEEEEETT it's finally time to use my brain again
1
3
1,918
eat your frogs first whatever task you hate the most, do it first thing in the morning, after that your whole day is easy
1
86
I gave eyes to steve he looked at me and described my clothes and the pigs steve's retinas cost 0$ and are powered by my m1 pro fastmlx + mlx-community/llava-v1.6-mistral-7b-4bit
1
6
1
17
2,442
We are excited to share #PDF2Audio, an open-source alternative to the #podcast feature of #NotebookLM with flexibility & tailored outputs that you can precisely control in the app: You can make a podcast, lecture, discussions, short/long form summaries & more, including the use of the amazing🍓o1 model (@sama @OpenAI: with stunning results!). Code & HF Space: You can find #PDF2Audio on GitHub for local use or try the Hugging Face space, all featuring @Gradio. Link to the repo & HF space in the reply. Thank you @knowsuchagencyfor the great work on #promptic and #pdf2podcast, as well as @LiteLLM, & @_akhaliq for helping us with the @huggingface spaces version. We hope that this tool is useful for the community. Background: Developing audio podcasts, lectures, & summaries from complex documents & data has become an exciting trend with impacts from research to education to business. Our open-source #PDF2Audio tool that allows users to utilize various models such as #o1 or local/open-source models, to develop deep-dives into technical content. Example application - material design analysis: As an example to show what the system can do, check the video for a detailed 13-minute analysis of one of the designs created by #SciAgents merging silk & dandelion pigments, created using 🍓o1. The conversation describes the new material, an integration of silk proteins & luteolin/dandelion pigments to create a new biomaterial. Silk, a natural #nanostructured protein-based fiber known for its strength & flexibility, is combined with dandelion pigments like luteolin, which offer unique optical properties. By merging these components at the nanoscale level, the resulting material displays structural coloration—vibrant, tunable colors created by the material's structure rather than synthetic dyes, and leverages silk's hierarchical organization as a scaffold for the pigments, ensuring uniform distribution and non-covalent bonding at the molecular level. Key technical features include: ➡️Low-temperature processing to maintain the integrity of both silk and pigments while reducing energy consumption by 30%. ➡️Enhanced mechanical properties, with tensile strength up to 1.5 gigapascals. ➡️Potential self-healing capabilities and environmental responsiveness, allowing the material to repair minor damage and change color based on environmental conditions. ➡️UV protection and antimicrobial properties, which make this material ideal for smart textiles, eco-friendly coatings, and medical applications. This development opens new doors for sustainable materials, offering an eco-friendly alternative to synthetic fibers with applications in various industries, from fashion to healthcare.
45
300
46
1,507
208,555
I asked Qwen2.5 to find us food in minecraft, here's what happened It was very creative and used the furnace as a weapon to smash a kebab [...] then forgot what the furnace was for in the first place! Running on mac thanks to @Prince_Canuma fastmlx, the whole LLM circuitry is done by @max_romana @kolbytn mindcraft
4
3
2
43
5,752
Announcing - WebGPU Puzzles: Learn GPU Programming in Your Browser It's a web app that let’s you practice writing GPU compute kernels using WebGPU - runs 100% in the browser, locally on your GPU (even tiny integrated laptop GPUs).
10
251
23
1,571
172,404
yessssssssssssssssssssss
After over 4 years of development, I’m excited to announce that #ChefRPG is finally released on Steam today in Early Access! Check it out here! store.steampowered.com/app/1… #pixelart #gamedevelopment
53
supermercat retweeted
My 8yo son built a Three.js site with zero coding experience He used Claude AI and let Cursor apply all the code for him. He actually made several projects including 2 platformer games, a drawing app, an animation app and an AI chat app. ~2 hours spent on each. I only helped him set up Cursor, Git and Netlify. Code is a design tool and you don’t even need to code anymore.
96
268
110
2,571
774,014
many crazy ml maths formulas actually look dead simple in code
51
the most underrated cursor feature?
56
cursor is like the sempai I have always wanted, I can annoy her as much as I want and she's always here to help for my homework
53