supermercat

@blockstranding @solana @sendaifun nice

The world's first onchain MMORPG goes live. On @solana. Block Stranding has completed its first large-scale multiplayer stress test! We rolled out an MCP build to set up sessions and connect AI agents. With the Solana Agent Kit from @sendaifun, each agent stayed responsive even under high TPS. The @magicblock real-time engine performed with overwhelming results. LLM-powered agents pushed 120K txs to devnet in 20 min, hitting >100 TPS! Onchain @solanagaming is cracked, we're beyond all prior limits.

@endel happy bday!!!

Today is my birthday 🥳🎂

@shizudio 🫡

Pushed my first front end code to app.perena.org interface. Super basic but still felt surreal. Spent years feeling guilty about straddling two worlds - the raw creativity of art and the structured innovation of tech. Society pushes us to specialize, to pick a lane. But lately I'm wondering if this divide is artificial. I felt the most productive when artistic instincts guide product decisions. Maybe we need more people who refuse to choose, who bring color to code and structure to creativity. The future isn't about art versus tech - it's about the beautiful chaos that happens when they collide.

Anchor v0.31.0 is finally out! It's likely going to be the last major release before v1. Highly recommend checking out the release notes before upgrading. github.com/coral-xyz/anch…

@Prince_Canuma @N8Programs 🫡

@N8Programs and @mwrites__ I showcased your amazing work built with FastMLX and MLX-VLM.

Thanks for having me! We spoke about Small Models and some of the amazing new developments with the MLX ecosystem :) Huge shout out for the organizers of Krakow Tech Summit.

@__acbraingenome @kaggle congrats !!!

When life hands you oranges, make….@kaggle Master tier! 🍊😎

@endel @colyseus very cool!!

I’m back! ☺️ And I can’t hold myself but share the initial concepts of what’s going to be @colyseus mascot for branding 😍 What do you think??

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.

pip install -U mlx

🎵🎶♥️ Shobii ♥️🎶🎵

@poetengineer__ takemamoney

visualize time-based media with gestures ✋✨🎥

@martin_casado Really cool! If you got LLMs negotiating between each other you got yourself a AI economy! (care for the infinite chat loop that will burn your credit card lol)

Using LLMs for NPC interaction is wild. All the shopkeepers now haggle for price, and only sell the item (returning a JSON object of the item) once a price is agreed upon.

sugoiiiiiiiii

@LMStudioAI <3

SHIEEEEEEETT it's finally time to use my brain again

eat your frogs first whatever task you hate the most, do it first thing in the morning, after that your whole day is easy

@nicochristie wow that's like 2 blocks of dirt high

i'm often asked how a 40inch vertical is relevant for a founder...

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

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.