Momo D NH

@Pirat_Nation Use pinhole and adblocker

YouTube is reportedlytesting unskippable ads up to 90 seconds long on smart TVs and streaming devices. • Up to 90-second ad breaks • No skip option • Designed mainly for TV viewing • Fewer, but longer ad interruptions • Higher ad revenue focus They want more users to pay for Premium

@minchoi @ollama Qwen is better!

Google's Gemma 4 is pretty wild. You can now run it locally with OpenClaw in 3 steps. 1. Install Ollama 2. Pull Gemma 4 model 3. Launch OpenClaw with Gemma as the backend Private local AI agents in minutes. Hardware guide: > E2B → any modern phones > E4B → most laptops > 26B A4B → Mac Studio 48GB+ RAM > 31B → Mac Studio 64GB+ RAM

@Alibaba_Qwen We need it available for OpenClaw, as I'm so struggling with Gemma 4 Is fast, but hallucinations are so frequently happening!

🏆 Qwen3.6-Plus just swept OpenRouter’s Daily, Weekly & Trending charts! The trial has wrapped. The model is fully live & production-ready. 📉 Lower latency | 🔥 Top-tier reasoning | 💰 Unmatched $/token value Keep shipping. Integrate now 👇 🔗 Model Studio：modelstudio.console.alibabacloud.com/ap-southeast-1… 🔗 OpenRouter: openrouter.ai/qwen/qwen3.6-p… 🔗 Fireworks AI: fireworks.ai/models/firewor… #OpenRouter #Qwen #AlibabaCloud #AI

@Alibaba_Qwen Please your Qwen 3.5 is much bette than Gemma 4! Can we have Qwen 3.6 plus 27B or 31B available open source for local use?!

🚀🚀

@Alibaba_Qwen Plese make it available locally and open source!!!

（1/8）🚀 Introducing Qwen3.6-Plus: Towards Real-World Agents! 🤖 Today, we’re thrilled to drop a major milestone in our journey toward native multimodal agents. Here is what makes Qwen3.6-Plus a game-changer： 💻 Next-level Agentic Coding: Smarter, faster execution. 👁️ Enhanced Multimodal Vision: Sharper perception & reasoning. 🏆 Top-tier Performance: Maintaining leading general capabilities. 📚 1M Context Window: Available by default via our API. Built on your invaluable feedback from the Qwen3.5 era, we’re laying a rock-solid foundation for real-world devs. Get ready to experience truly transformative ✨ Vibe Coding ✨. Huge thanks to our community! Go try it out and show us what you can build. 👇 Chat: chat.qwen.ai API: modelstudio.console.alibabacloud.com/ap-southeast-1… Blog: qwen.ai/blog?id=qwen3.6 🔔Noted：More Qwen3.6 models to come and be open-sourced! Stay tuned~ 👀#Qwen #AI #AgenticCoding #VibeCoding #Agents

@AlexFinn @petergyang So Alex, how can we contribute to make things better and pussh it further, cheers from Canada!

@petergyang Both are 100% true

Both of these can be true: 1. No model is anywhere near as good as Opus for OpenClaw 2. Using Claude Code as a personal assistant replacement is OK but just doesn’t feel as “mine” as my OpenClaw

@heydave7 Qwen 3.5 is much better while Gemma is super fast!

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

@VadimStrizheus @trq212 I agree! Which is kinda sad. I hope OpenAi will bring sthing better with chatGPT 5.5 or .6!

@moubuntu @trq212 It’s not the same codex feels dumber to me

@trq212 what the heck if this?! i bought a second Claude Max plan 5x this time, and in the span of 40 minutes i've used up my entire 5 hour session limit? and its at 42% for my weekly limit?? p.s i've only been coding inside my terminal this whole time, no OpenClaw, no Hermes agent, nothing attached to the Claude sub.

@RobertJBye Why it is NOT working, I'm of this!!! Please fix it

If you’re into harnesses, orchestration, sandboxes, and tools. This one is for you.

@trq212 Why it is NOT working, I'm of this!!! Please fix it

you'll need to explicitly prompt Claude Code to use it, but the Monitor Tool is super powerful e.g. "start my dev server and use the MonitorTool to observe for errors"

@AnthropicAI Why it is NOT working, I'm of this!!! Please fix it

New on the Engineering Blog: Building Managed Agents—our hosted service for long-running agents—meant solving an old problem in computing: how to design a system for “programs as yet unthought of.” Read more: anthropic.com/engineering/ma…

@RoundtableSpace @MarioNawfal WTF? !

CLAUDE OPUS 4.6 THINKING REDUCED BY 67% - Data shows Claude Opus 4.6 now thinks 67% less than before, dubbed “AI shrinkflation” - Same price but noticeably dumber; users report more guardrails and restricted output - Anthropic stayed silent until public data dropped; suspected compute-saving for next model (Mythos)

@TiffanyFong Bravo 👏 how's that?!

holy shit i made it to 520K without posting my titties on the internet! 🎉

@Itsfoss That's a nice move ✌️😉

Anthropic has donated to the Apache Software Foundation. 💰 itsfoss.com/news/anthropic…

Linus Torvalds, the legend 🔥

@CryptoLifer33 Check the movie 🍿🎥 take me to the moon 🌝🌛

Nasa lol

@CryptoLifer33 @TheMoonCarl Exactly 💯

@TiffanyFong Amazing 🤩

This video’s racked up 1M views in an HOUR made in Seedance 2 with Higgsfield. & the wildest part? It’s fully original. AI personalities are reaching audiences at scale.