Today we are introducing a Python SDK for Mac's on-device LLM! https://t.co/LQVp2EheLO https://t.co/mcJh9M1DaW

Introducing Faster Qwen3TTS! Realistic voice generation at 4x real time: - Same amazing voice quality from Qwen's model - Streaming support with <200 ms to first audio - 5x faster than the official implementation Just pip install faster-qwen3-tts Try the demo! https://t.co/Dcf9jNXz8g

Ollama can now launch Pi, a minimal coding agent which you can customize for your workflow ollama launch pi You can even ask pi to write extensions for itself https://t.co/hlUYnA3vl4

Meet Qwen3-Voice-Embedding: a powerful voice identity model that extracts unique speaker signatures from audio. It's like a fingerprint scanner for voices, and it's optimized for real-time applications. This is a game-changer for voice tech! https://t.co/HEPUpu0QF6

Train your 🦞@openclaw simply by talking to it. Meet OpenClaw-RL. Host your model on our RL server, and your LLM gets optimized automatically. Use it anywhere. Keep it private. Make it more personal every day. We have fully open sourced everything. Come in and have fun!

We open sourced an operating system for ai agents 137k lines of rust, MIT licensed we love @openclaw and it inspired a lot of what we built. but we wanted something that works at the kernel level so we built @openfangg agents run inside WASM sandboxes the same way processes run on linux. the kernel schedules them, isolates them, meters their resources, and kills them if they go rogue. it has 16 security layers baked into the core. WASM sandboxing, merkle hash-chain audit trails, taint tracking on secrets, signed agent manifests, prompt injection detection, SSRF protection, and more. every layer works independently. giving an LLM tools with zero isolation is insane and we're not doing it. we also created something called Hands. right now every ai agent is a chatbot that waits for you to type. Hands are different. you activate one and it runs on a schedule, 24/7, no prompting needed. your Lead Hand finds and scores prospects every morning and delivers them to your telegram before you wake up. your Researcher Hand writes cited reports while you sleep. your Collector Hand monitors targets and builds knowledge graphs continuously. they work for you. you don't babysit them https://t.co/4xYzMAYgmb ⭐

Beyond the winners of our "Built with Opus 4.6 Claude Code Hackathon," there were so many amazing projects that deserve a shoutout. Today I want to highlight Pasal by Ilham Putra. 280 million Indonesians can't easily search their own laws. Pasal fixes that. https://t.co/VJcMj3BwHO

Introducing MLX-Swift-TS https://t.co/TDCJXVpago An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined @datadoghq , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to @awnihannun and the MLX team for building MLX and its Swift API, @Prince_Canuma for inspiration on MLX SDK patterns, and @atalwalkar and the Datadog team for Toto.

Introducing MLX-Swift-TS https://t.co/TDCJXVpago An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined @datadoghq , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to @awnihannun and the MLX team for building MLX and its Swift API, @Prince_Canuma for inspiration on MLX SDK patterns, and @atalwalkar and the Datadog team for Toto.

🚨 Anthropic just open-sourced the exact Skills library their own engineers use internally. Stop building Claude workflows from scratch. These are plug-and-play components that work across Claude Code, API, SDK, and VS Code copy once, deploy everywhere. What's inside: → Excel + PowerPoint generation out of the box → File handling and document workflows → MCP-ready subagent building blocks → Pre-built patterns for multi-step automation → Production templates you'd normally spend weeks writing The old way: re-explain your workflow every single chat. The new way: build a Skill once, Claude never forgets how you work. 100% Open Source. Official Anthropic release. Repo: https://t.co/XNx3i4yNy6

Meet Whisper-SAM: a specialized speech recognition model that's turning heads. It's a fine-tuned version of OpenAI's Whisper-small, optimized for automatic speech transcription. Perfect for developers who need accurate, efficient audio-to-text conversion without the heavy compute.

1/4 We are thrilled to announce that CoPaw is now open source! After an incredible wave of feedback, our team has completely overhauled the engine to give you full control over your personal AI partner. Key Highlights: Ultimate Model Freedom Local-First: Full native support for Ollama, llama.cpp, and MLX (Apple Silicon). Bring Your Own Model: Easily add/remove custom model providers or private API endpoints. Your data, your choice. Smarter Long-Term Memory No more "amnesia." CoPaw remembers your preferences and tasks. New Local Mode: Use vector search without complex database installs—now fully compatible with Windows for an out-of-the-box experience. Modular "Lego-Like" Architecture Skill Hub Integration: Import skills from community hubs like ClawHub with one command. Agentic Workflow: Modularized Prompts, Hooks, and Tools. Supports MCP (Model Context Protocol) hot-swapping—expand capabilities without restarting. Proactive Multi-Channel Connection Connect to DingTalk, Feishu, Discord, iMessage, and more. A new standardized protocol makes it easier than ever to build your own channel plugins.

Qwen3.5 is now updated with improved tool-calling & coding performance! Run Qwen3.5-35B-A3B on 22GB RAM. See improvements via Claude Code, Codex. We also benchmarked GGUFs & removed MXFP4 layers from 3 quants. GGUFs: https://t.co/4lSce5zZbO Analysis: https://t.co/rHZK8JWdYM

Alibaba has expanded its Qwen3.5 model family with 3 new models - the 27B model is a standout, scoring 42 on the Artificial Analysis Intelligence Index and matching open weights models 8-25x its size @Alibaba_Qwen has expanded the Qwen3.5 family with three new models alongside the 397B flagship released earlier this month: the Qwen3.5 27B (Dense, scoring 42 on Intelligence Index), Qwen3.5 122B A10B (MoE, 42), and Qwen3.5 35B A3B (MoE, 37). The two MoE (Mixture-of-Experts) models only activate a fraction of the total parameters per forward pass (10B of 122B and ~3B of 35B respectively). The Intelligence Index is our synthesis metric incorporating 10 evaluations covering general reasoning, agentic tasks, coding, and scientific reasoning. All models are Apache 2.0 licensed, natively support 262K context, and return to the unified thinking/non-thinking hybrid architecture from the original Qwen3, after Alibaba moved to separate Instruct and Reasoning checkpoints with the Qwen3 2507 updates. Key benchmarking results for the reasoning variants: ➤ Qwen3.5 27B scores 42 on Intelligence Index and is the most intelligent model under 230B. The nearest model of similar size is GLM-4.7-Flash (31B total, 3B active) which scores 30. Open weights models of equivalent intelligence are 8-25x larger in terms of total parameters: MiniMax-M2.5 (230B, 42), DeepSeek V3.2 (685B, 42), and GLM-4.7 (357B, 42). In FP8 precision it takes ~27GB to store the model weights, while in 4-bit quantization you can use laptop quality hardware with 16GB+ of RAM ➤ Qwen3.5 27B scores 1205 on GDPval-AA (Agentic Real-World Work Tasks), placing it alongside larger models. For context, MiniMax-M2.5 scores 1206, GLM-4.7 (Reasoning) scores 1200, and DeepSeek V3.2 (Reasoning) scores 1194. This is particularly notable for a 27B parameter model and suggests strong agentic capability for its size. GDPval-AA tests models on real-world tasks across 44 occupations and 9 major industries ➤ AA-Omniscience remains a relative weakness across the Qwen3.5 family, driven primarily by lower accuracy rather than hallucination rate. Qwen3.5 27B scores -42 on AA-Omniscience, comparable to MiniMax-M2.5 (-40) but behind DeepSeek V3.2 (-21) and GLM-4.7 (-35). Although Qwen3.5 27B's hallucination rate (80%) is lower than peers (GLM-4.7 90%, MiniMax 89%, DeepSeek 82%), its accuracy is also lower at 21% vs 34% for DeepSeek V3.2 and 29% for GLM-4.7. This is likely a consequence of model size - we have generally observed that models with more total parameters perform better on accuracy in AA-Omniscience, as broader knowledge recall benefits from larger parameter counts ➤ Qwen3.5 27B is equivalently intelligent to Qwen3.5 122B A10B. The 122B A10B is a Mixture-of-Experts model that only activates 10B of its 122B total parameters per forward pass. The 27B model leads in GDPval-AA (1205 Elo vs 1145 Elo) and slightly on TerminalBench (+1.5 p.p.), while the 122B model leads on SciCode (+2.5 p.p.), HLE (+1.2 p.p.), and has a lower hallucination rate (Omniscience -40 vs -42) ➤ Qwen3.5 35B A3B (Reasoning, 37) is the most intelligent model with ~3B active parameters, 7 points ahead of GLM-4.7-Flash (30). Other models in this ~3B active category include Qwen3 Coder Next (80B total, 28), Qwen3 Next 80B A3B (27), and NVIDIA Nemotron 3 Nano 30B A3B (24) ➤ Qwen3.5 27B used 98M output tokens to run the Intelligence Index, costing ~$299 via Alibaba Cloud API. This is notably high token usage compared to models at similar intelligence: MiniMax-M2.5 (56M), DeepSeek V3.2 (61M), and even the larger Qwen3.5 397B (86M). Other information: ➤ Context window: 262K tokens (extendable to 1M via YaRN) ➤ License: Apache 2.0 ➤ API pricing (Alibaba Cloud): 397B: $0.60/$3.60, 122B: $0.40/$3.20, 27B: $0.30/$2.40, 35B A3B: $0.25/$2.00 per 1M input/output tokens

I had the same thought so I've been playing with it in nanochat. E.g. here's 8 agents (4 claude, 4 codex), with 1 GPU each running nanochat experiments (trying to delete logit softcap without regression). The TLDR is that it doesn't work and it's a mess... but it's still very pretty to look at :) I tried a few setups: 8 independent solo researchers, 1 chief scientist giving work to 8 junior researchers, etc. Each research program is a git branch, each scientist forks it into a feature branch, git worktrees for isolation, simple files for comms, skip Docker/VMs for simplicity atm (I find that instructions are enough to prevent interference). Research org runs in tmux window grids of interactive sessions (like Teams) so that it's pretty to look at, see their individual work, and "take over" if needed, i.e. no -p. But ok the reason it doesn't work so far is that the agents' ideas are just pretty bad out of the box, even at highest intelligence. They don't think carefully though experiment design, they run a bit non-sensical variations, they don't create strong baselines and ablate things properly, they don't carefully control for runtime or flops. (just as an example, an agent yesterday "discovered" that increasing the hidden size of the network improves the validation loss, which is a totally spurious result given that a bigger network will have a lower validation loss in the infinite data regime, but then it also trains for a lot longer, it's not clear why I had to come in to point that out). They are very good at implementing any given well-scoped and described idea but they don't creatively generate them. But the goal is that you are now programming an organization (e.g. a "research org") and its individual agents, so the "source code" is the collection of prompts, skills, tools, etc. and processes that make it up. E.g. a daily standup in the morning is now part of the "org code". And optimizing nanochat pretraining is just one of the many tasks (almost like an eval). Then - given an arbitrary task, how quickly does your research org generate progress on it?

In the next version of Claude Code.. We're introducing two new Skills: /simplify and /batch. I have been using both daily, and am excited to share them with everyone. Combined, these kills automate much of the work it used to take to (1) shepherd a pull request to production and (2) perform straightforward, parallelizable code migrations.

Yaay! 🎉 4k+ downloads and 460+ stars! Building this has been a wild ride. If you have an Apple Silicon Mac and want to fine-tune LLMs locally without changing your original Unsloth code, come join the party. https://t.co/ZPrwcJyrd8

Rust implementation for Speech-to-Text based on open-source Qwen3 models * Self-contained binary build — no external dependencies * Uses libtorch on Linux with optional Nvidia GPU support * Uses MLX on MacOS with Apple GPU/NPU support 🔨 CLI for AI agents and humans: https://t.co/knsZlastgQ 🖥️ OpenAI compatible API server: https://t.co/qjDqCf9hor 🤖 OpenClaw skill: https://t.co/tE6lzTjYpy Why and how https://t.co/VxRt9oSZ8a

High-performance browser control for AI agents. Pinchtab is a lightweight (12MB) Go binary that runs Chrome and exposes a plain HTTP API so any agent or script can navigate web pages, read text efficiently, click/type interactively, and persist sessions. Zero config, framework-agnostic, token-efficient.

New Engineering blog: We tasked Opus 4.6 using agent teams to build a C compiler. Then we (mostly) walked away. Two weeks later, it worked on the Linux kernel. Here's what it taught us about the future of autonomous software development. Read more: https://t.co/htX0wl4wIf https://t.co/N2e9t5Z6Rm

https://t.co/G6PemSZqwN

¿Pero qué maravilla es esta? https://t.co/NK4PVYFKg2

#youtube George Hotz | Programming | how I actually use agentic coding | Agentic AI https://t.co/rrloPO5Vif

Use my tscribe tool to easily transcribe X or Youtube videos... Great way to get transcripts into your claude code sessions... Simply... tscribe transcribe <video url> then just dump it to stdout (lots more you can do too...) tscribe dump