Rahul Goyal

The Clarity Playbook — Our debut book is now live! How Busy Professionals Can Think Better, Decide Faster, and Lead. A 91-page field guide packed with 7 high-leverage frameworks used in global boardrooms & designed for clarity that you can use today. rahulgoyal.co/the-clarity-pl…

@MilksandMatcha Building muscles for my OpenClaw.

Giving away 5 Codex Pro plans Each person will get 3 months of free Codex Pro (highest tier). Winners will be selected from comments in 48 hours, comment below why you want it.

Starting my @YouTube journey with Hermes, OpenClaw, and others. Video coming soon!! Subscribe @rahulgoyalco" target="_blank" rel="nofollow noopener">youtube.com/@rahulgoyalco

@Alibaba_Qwen Sound promises… What is the size? Any small for a 16G Mac mini?

🚀 Qwen3.5-Omni is here! Scaling up to a native omni-modal AGI. Meet the next generation of Qwen, designed for native text, image, audio, and video understanding, with major advances in both intelligence and real-time interaction. A standout feature: 'Audio-Visual Vibe Coding'. Describe your vision to the camera, and Qwen3.5-Omni-Plus instantly builds a functional website or game for you. Offline Highlights: 🎬 Script-Level Captioning: Generate detailed video scripts with timestamps, scene cuts & speaker mapping. 🏆 SOTA Performance: Outperform Gemini-3.1 Pro in audio and matches its audio-visual understanding. 🧠 Massive Capacity: Natively handle up to 10h of audio or 400s of 720p video, trained on 100M+ hours of data. 🌍 Global Reach: Recognize 113 languages (speech) & speaks 36. Real-time Features: 🎙️ Fine-Grained Voice Control: Adjust emotion, pace, and volume in real-time. 🔍 Built-in Web Search & complex function calling. 👤 Voice Cloning: Customize your AI's voice from a short sample, with engineering rollout coming soon. 💬 Human-like Conversation: Smart turn-taking that understands real intent and ignores noise. The Qwen3.5-Omni family includes Plus, Flash, and Light variants. Try it out: Blog: qwen.ai/blog?id=qwen3.… Realtime Interaction: click the VoiceChat/VideoChat button (bottom-right): chat.qwen.ai HF-Demo: huggingface.co/spaces/Qwen/Qw… HF-VoiceOnline-Demo: huggingface.co/spaces/Qwen/Qw… API-Offline: alibabacloud.com/help/en/model-… API-Realtime: alibabacloud.com/help/en/model-…

@yourchinaguy @openclaw @steipete After months of trials and errors, I can say confidently that the model plays a huge role in the @openclaw experience.

I set up my @openclaw, gave it 3 cron tasks After day 1 it started breaking and didn’t give me anything for 5 days. I just sent it a message “hey, I will look into this later, don’t worry about it” 1 day later it somehow resumes without me doing anything I love it @steipete

I migrated my list from Kit to @Substack. It says the open rate is less, and they blocked it. Now, the expectation is to send an email to everyone. Only those who will confirm will be part of the list. I wish @beehiiv would give 10K subs in the free plan, or until we monetise.

@sundarpichai Last time, I checked it was not available in the UK. Hope it’s coming soon? Like Gmail became the go-to mail for everyone, probably we should have Amail for agents.

2004 was a good year, but your Gmail address doesn't need to be stuck in it. To say goodbye to v0t3f0rp3dr02004@gmail.com or mrbrightside416@gmail.com (or whatever you were into at the time), go to your Google Account settings and choose any name available. You'll keep your old username and you can sign in with both.

🐙 Everyone says @openclaw is not secure on the main PC as it has root access, etc. Then, do I have Junior OC? It can’t go even beyond the workspace. I have given all access and permission possible. The sandbox is off; I want it to control and don’t ask me anything.

Learn Faster, Try Harder! Failure is far better than not trying or waiting for the perfect moment.

@RishiSunak @thetimes The TV licence applies when watching the BBC. While I don’t have complete data, I suspect even the BBC’s reach through its YouTube channel could surpass TV broadcasting in many hours.

YouTube’s reach in Britain now exceeds all BBC channels combined. The BBC must adapt to the way people consume content today. My column in @thetimes 👇 thetimes.com/business/compa…

This summer with Agents! Let’s ready AI Agents, so we can manage from the beach.

There was a good reason @openclaw earlier was called ClawdBot; literally, it works best with Anthropic Claude. I mean, it’s good with Codex, MiniMax, and I am running with a local model as well, but if you do the first setup and initial foundation with Claude, it will be faster and cleaner. It will feel like real hatching; otherwise, it might feel like patching.

@cjpedregal @meetgranola Congratulations..

Today we're announcing our Series C alongside some big updates that make @meetgranola better for your team and your tools. Excited to partner with Danny at Index and Mamoon at KP. Big things to come. Back to work!

Resilience isn't about never falling, it's about rising every time you do. Small steps forward, consistently taken, are how mountains get moved.

It would be great on a 16GB mac mini m2 pro. I was settling with QWEN3.5:9B; now it’s time to scale.

@LottoLabs Yeah, but with OpenClaw it’s good for small tasks, not for long tasks.

@RahulGoyalco 9b is a decent model, follows skills well, can use tool calls, it’s good for the size

Qwen 3.5 27b never degrades, never stops running, never has token limits, never refuses, never logs my prompts, never trains on my data, never sells my data, never runs up my credit card

@LottoLabs Yeah, I guess so. I am running qwen3.5:9b

@RahulGoyalco It will, but not well

@HHaandr @RevenueCat @BusDownBonnor Sounds cool.

🏰Prepping for the next @RevenueCat Houseparty. in London Taking suggestions on iconic co-hosts (after @BusDownBonnor put the bar sky-high in SF earlier this month!)

It would be good if @ouraring can give MCP/CLI/API to analyse data outside the app.

@denk_tweets This world would be great. Let me set up with OpenClaw.

🚢🚢🚢