Real-time audio transcription. Entirely on-device. This hands-on tutorial shows you how to build it from scratch. No cloud dependencies, no API calls, complete privacy, using LFM2-Audio-1.5B by Liquid AI Enjoy ↓ github.com/Liquid4All/coo…

> top 8 local LLMs to run at home for December 2025 - updated > Devstral-2-123B at 1st place > senior engineer energy > not flashy, just relentlessly effective > this is the model i trust when i need results > just “fix the thing” > agentic coding is the real superpower > clean

Open source canva ai alternative

Last Issue of DSPyWeekly for 2025 - Issue 16th 📚 Articles Stop Writing Prompts Like a Medieval Alchemist: Why it's time to ditch the "alchemy" for programmable modules. The Meta-Prompting Protocol: Orchestrating LLMs with adversarial feedback loops. 🎥 Videos DSPy in Rust:

Algorithmic trading is the domain of secretive hedge funds and banks. Python unlocked these secrets for everyone (even Goldman Sachs has an open-source tool). Use the same tools the professionals use. Here are 17 Python libraries that open the black box:

Simple RL is all you need for Small LMs This paper shows that a single simple RL recipe can push 1.5B models to SoTA reasoning with half the compute Suggesting whether today’s complex RL pipelines are solving real problems or ones we created ourselves.. trending on alphaXiv📈

This release was only possible by the numerous MedARC volunteers who implemented benchmarks and datasets to evaluate with. Grateful to all those who contributed!

"When Reasoning Meets Its Laws" This paper proposed a simple "laws of reasoning": AI model's reasoning should scale linearly with question complexity and when trained to obey this principle (with complexity measured with monotonicity and compositionality), their reasoning

Qwen Congrats guys this is an amazing open-source effort! 💜🥰 We made Qwen-Image-Edit-2511 GGUFs so everyone can run it locally! 🙏 huggingface.co/unsloth/Qwen-I…

Desktop charting for crypto markets github.com/flowsurface-rs…

"The Prism Hypothesis" This new paper shows that image meaning mostly lives in low-frequency signals, while details like textures live in high frequencies By exploiting this split, the authors build a single latent space that supports both understanding (CLIP-style) and

If you want to learn AI the right way, start here. No shortcuts. No hype. No fluff. Top 10 Stanford's Courses on AI & ML. CS221: Artificial Intelligence CS229: Machine Learning CS229M: Machine Learning Theory CS230: Deep Learning CS234: Reinforcement Learning CS224N: Natural

Attention Is Not What You Need This paper replaces self-attention with Grassmann Flows: a linear-time sequential model based on low-rank geometric flows on a Grassmann manifold. Early results show competitive performance with Transformers, with potentially better scaling and a

I spent all of Christmas reverse engineering Claude Chrome so it would work with remote browsers. Here's how Anthropic taught Claude how to browse the web (1/7)

Happy New Year! I've just launched my coding agent orchestrator, Gas Town, for anyone crazy enough to try it. steve-yegge.medium.com/welcome-to-gas…

Today in Nature Medicine we report that AI can predict 130 diseases from 1 night of sleep🛌 We trained a foundation model (#SleepFM) on 585K hours of sleep recordings from 65K people—brain, heart, muscle & breathing signals combined. AI learns the language of sleep🧵

NotebookLM + Google Gemini FULL COURSE 3 HOURS (Build & Automate Anything)

Explore it here: opensourceprojects.dev/post/15217dc5-…

Happy Friday! 🎉 This week’s DSPyWeekly is a dedicated special edition: The RLM (Recursive Language Models) Playbook. Everything you need to catch up: 📄 The Original Paper + Simple Explainers 🎥 Video deep dive with Alex L Zhang ❌ The Do's and Don'ts of RLMs from usage

Continual learning is being positioned as a prerequisite for AGI (i.e., general systems must be adaptable). I spent a large part of graduate school working on continual learning. Over the last month I've revisited the literature, considered its connections / relevance to LLMs,