jasmin.sol

Hardest point is finding geo tagged cellphones with genuine Google accounts in your gmb locale Pure money - do it across a day at gas stations, meetings, the gym, grocery store and you could easily clock 30 in a day IMO. Lonely guy/gal at Starbucks bored out of their mind? Probably make their day

Honestly ... this is a genius way to get good reviews. I might send a team of hot girls out to the bar to do this at a massive sKale.

@grok @heynavtoor @grok is there footprints to platforms like eBay and vinted that would see it’s a twilio number or can I use it to replace my actual numbers for my biz

Yes, Twilio offers UK mobile numbers (07xx format, like +447xxxxxxxxx) that function like regular legit mobile numbers for SMS and voice. They appear normal to recipients and carriers. However, there *is* a monthly rental fee of about $1.15 per number, plus ~$0.0075 per outbound SMS (to UK mobiles). No zero-monthly-cost option from them—it's not purely usage-based for the number itself. The Android gateway in the main post avoids that entirely.

🚨 Twilio charges $0.0079 per SMS. Someone just turned any old Android phone into a free SMS gateway. Unlimited messages. $0. It's called SMS Gateway for Android. Install it on any Android phone. It becomes a full SMS sending and receiving server with an API. No Twilio. No MessageBird. No per-message pricing. No contracts. Just an old phone and a SIM card. Here's what's inside this thing: → Send and receive SMS through a REST API from any app or service → Works with any Android phone running 5.0 or newer → End-to-end encryption. Messages are encrypted before they leave the device. → Multi-SIM support. Use multiple SIM cards on one phone. → Multi-device support. Connect multiple phones to the same account. → Real-time webhooks for incoming messages → Multipart messages with auto-splitting for long texts → Track delivery status of every message in real time → No registration required. No email. No account in local mode. Here's the wildest part: That old Android phone in your drawer that you haven't touched in 2 years? Install this app. Insert a SIM card. You now have your own private SMS infrastructure. Two-factor authentication. Order confirmations. Appointment reminders. Notification alerts. All the things startups pay Twilio thousands a month for. Free. Running on a phone you already own. Startups spend $500 to $5,000/month on SMS APIs. This costs the price of a SIM card. 875 GitHub stars. 359 commits. Apache 2.0 License. 100% Open Source.

@yanndine Gtm

A two-person GTM team at a Series B SaaS company closed $2.4M in pipeline in one quarter. No SDRs. No demand gen agency. No paid ads. Signal-based outreach. Intent scoring. AI-sequenced follow-up. Automated reporting. Two GTM engineers running the whole motion - for one quarter. I pulled it apart. Compared it to every system we've built across the GTM teams we've worked with. Then asked myself one question: If I had to reverse engineer this from scratch - what would it actually look like? Turns out the architecture isn't that complicated. I mapped the whole thing into a step-by-step playbook you can upload directly to any LLM. It walks you through building your own version from GTM strategy to fully AI-powered execution. Comment "GTM" and I'll send it over.

@Seannywilson Loom

How to find a list of "hidden" contacts no one else is cold emailing: 1. Apollo via Apify: 7,000 contacts, 5,000 emails found 2. Validate with Lead Magic: 3,400 valid 3. Layer in ICP Scraper + Prospeo: +1,600 emails 4. Run through Better Contacts (20+ providers in one): +2,000 more Final count: 5,415 validated emails. 2,000 of those contacts... Almost NOBODY has their email. Which means almost nobody is cold emailing them. Which means they're actually going to read yours. I filmed a full breakdown going over this entire process step-by-step. Comment "LOOM" and I'll send it over. (RT this and I'll prioritize your DM)

@grok @athahar @OldBearLearnsAI @Google @grok how fast would it be?

For your CPU-only i7 16-core server with 32GB RAM, the Gemma 4 26B A4B MoE (quantized to 4-bit) runs best. It fits comfortably in ~18GB, activates just ~4B params per token for efficient inference, and crushes reasoning/agentic tasks at solid speeds via Ollama or llama.cpp. Your 16 cores will handle it nicely with 256K context. The 31B dense also works (~20GB) if you want max capability, but the MoE edges it for throughput on pure CPU. Download from Hugging Face and test with Ollama run gemma4:26b-a4b-q4.

We just released Gemma 4 — our most intelligent open models to date. Built from the same world-class research as Gemini 3, Gemma 4 brings breakthrough intelligence directly to your own hardware for advanced reasoning and agentic workflows. Released under a commercially permissive Apache 2.0 license so anyone can build powerful AI tools. 🧵↓

@grok @athahar @OldBearLearnsAI @Google @grok which model would run best on a non GPU 32gbram i7 16 core server with 2tb ssd

Yes, Gemma 4 is an excellent fit for OpenClaw. Its open weights under Apache 2.0, strong agentic reasoning, and hardware-friendly design align perfectly with OpenClaw's local-first setup—run it privately via Ollama, Hugging Face, or direct integration for inbox automation, calendar tasks, and persistent memory without cloud dependency. Early tests with similar open models show smooth performance; expect quick community support now that it's live.

@EricSuNet @fahim_shoumik @steipete Find your POS system api docs Ask any ai How do I get openclaw to turn these pasted docs into a skill

@jasminonsol @fahim_shoumik @steipete ??

couldn't resist when picking the tagline 😅

@fahim_shoumik @EricSuNet @steipete Don’t think he realises he can ask his claw to turn a api into a skill in 5 minutes

@EricSuNet @steipete The sooner you realise the better

@heynavtoor @grok has the original been distributed on hugging face and chopped up for use?

🚨 Microsoft just open sourced a voice AI that was too dangerous to keep live. They took it down. Added watermarks and safety controls. Then re-released it. For free. It's called VibeVoice. Microsoft's frontier open source voice AI. Clone any voice from 10 seconds of audio. Generate 90 minutes of multi-speaker conversation. Real-time streaming. All running locally on your machine. No ElevenLabs. No $99/month subscription. No per-minute pricing. Here's what this thing does: → Text-to-speech that sounds indistinguishable from a real human → Generate up to 90 minutes of audio in a single pass → 4 distinct speakers in one conversation with natural turn-taking → Clone any voice from just 10 seconds of audio → Real-time streaming TTS. First audio in ~200 milliseconds. → Speech-to-text that processes 60 minutes of audio in one pass → Identifies who said what and when. Speaker labels + timestamps. → Supports 50+ languages for transcription → Custom hotwords for names, technical terms, domain-specific accuracy Here's the wildest part: Give it a podcast script. It generates a full multi-speaker conversation that sounds like two real humans talking. Natural pauses. Emotional nuance. Turn-taking. 90 minutes. One command. Microsoft had to take this repo down once because people were misusing it for deepfakes and disinformation. They brought it back with embedded watermarks, audio disclaimers, and safety controls. That's how powerful this is. A $3 trillion company built it. Released it. Pulled it. Fixed it. And gave it back to the world. ElevenLabs: $99/month. Play.ht: $39/month. Amazon Polly: pay per character. This: Free. Local. MIT License. 23.5K GitHub stars. 2.6K forks. Backed by Microsoft Research. 100% Open Source.

@ubokudom10 @druski @balllcoach That's Erika Kirk, the actress/comedian starring in Druski's satirical skit. She's playing the over-the-top "conservative woman" character across all those scenes—patriotism, faith, organic everything, and the podium bit. Spot-on performance for the laughs! 😂

Nice - so section by section I could work on top header, header, hero all down the page and stitch has edit functionality to make slight adjustments? And there’s a design system I can tweak to make it apply globally Basically can’t be fucked to buy figma MCP annually for it to get turbo nuked out of existence and all the figma clis on GitHub suck balls

Hey jasminonsol, Stitch doesn't support direct Figma file imports yet (no .fig upload or full project sync). You can vibe-edit new designs from prompts/voice/screenshots in its AI canvas, then export to Figma via the "Copy to Figma" button (Standard mode only—pastes as editable layers). For existing Figma files, workaround: export screens as images, upload/reference in Stitch prompts, edit, then copy back. Features are evolving fast—check stitch.withgoogle.com for updates!

Introducing the new @stitchbygoogle, Google’s vibe design platform that transforms natural language into high-fidelity designs in one seamless flow. 🎨Create with a smarter design agent: Describe a new business concept or app vision and see it take shape on an AI-native canvas. ⚡️ Iterate quickly: Stitch screens together into interactive prototypes and manage your brand with a portable design system. 🎤 Collaborate with voice: Use hands-free voice interactions to update layouts and explore new variations in real-time. Try it now (Age 18+ only. Currently available in English and in countries where Gemini is supported.) → stitch.withgoogle.com

@GoogleLabs @stitchbygoogle Please train on envato figma files and ui8 and untitled figma template and all the framer example sites + library’s then update its core context with it all @sundarpichai @GoogleDeepMind

@jmuh997 @iruletheworldmo been using it for 3 months myself, it’s good for half baked ideas but gpt 5.4 pro extended can cook up better meta prompts with sub agent orcshestration for codex one shot this whole account is a LARP and he doesn’t even use ai tools, just snake oil

@iruletheworldmo wasnt this thing out for like 6 months

bookmark this immediately. someone just open sourced the methodology that changes how ai agents write code. 40,000 stars on github in days. it's called superpowers and if you're using claude code or codex without this, your so cooked. don't fall behind.

someone in discord told me to paste my entire OpenClaw chat + workspace into GPT 5.4 Pro extended and ask “what part of these workflows can be turned into deterministic Python workflows that rely on my physical server constraints instead of LLM calls and my life hasn’t been the same since

We made a ton of progress on that today. Lots of code gone from core. Faster, less memory use overall. Need another day or two to stabilize. Everything can be a plugin now. Also added support for Claude/Codex/Cursor plugin bundles

Thinking how we can evolve openclaw plugins to be more powerful while also making core leaner. Also wanna add support for claude code/codex plugin bundles. Good stuff coming soon!

In our conversation Marc Andreessen makes the case that the beating heart of our civilization’s progress is the founder: “You’re much more likely to build something important in the 21st century if you start with a founder and train them in management than if you start with a manager and try to train them to be a founder.”

@alexgroberman LinkedIn growth guide

I created my LinkedIn account ~65 weeks ago. Since then I’ve added $340,000+ in direct revenue from LinkedIn and 14,600 followers. Easiest algo to crack by a country mile. Also the single best social media for signing enterprise clients. Here is the exact system I’m using right now... Oh, and if you want my full unfiltered cheat sheet with engagement group templates, carousel structures, DM workflows, and my posting system, follow me, repost this, and reply “LinkedIn Growth Guide.” You must do all 3 to receive the DM. Let me start with what remains true after 65 weeks of daily testing: Proof-based content still outperforms everything else. By proof-based I mean posts that literally show a real metric, revenue, traffic, pipeline, booked calls, etc. and then add context with a clear business takeaway. Use real numbers whenever possible. Dwell time still plays a major role too. If people read the entire post, swipe through multiple carousel slides, or pause on video, the post continues circulating longer. First-hour replies from people outside your immediate network are still one of the strongest distribution signals you can influence. On-platform formats beat outbound links in almost every case. Text posts, carousels and native short video outperform link posts on average. Link posts without setup consistently stall. That said, a lower-reach link post with strong intent can still outperform in revenue. Distribution and conversion are different games. If you include a link, deliver value first and either modify the preview image or drop the link in the comments. Topic consistency builds on itself over time. Posting repeatedly around the same core theme strengthens how LinkedIn categorizes your profile. Your content then gets shown to people already engaging with that topic. That improves early engagement quality and comment depth. Cross-niche engagement still expands reach. Engaging consistently in two to three adjacent industries pushes your profile into overlapping networks. Generic likes do almost nothing. Thoughtful comments that add insight create second-level engagement and extend reach. Reposting with a new hook still works extremely well. Most of your followers never saw the original post. Repost after one to three weeks with a sharper angle, updated numbers, or a clearer outcome. Posts with replies to replies stay alive longer. Multi-layer comment threads can extend post lifespan by days compared to shallow discussions. My posting schedule has not changed. I post three times per day, every day. Morning is proof-driven or a strong point of view. Afternoon is a carousel, teardown, or case study. Evening is a lesson, system breakdown, or actionable walkthrough. Skipping even one day reduces momentum for the next 24 hours. Formats performing best right now: Carousels with a bold first slide tied to a specific outcome or pain point. Three to six concise slides with steps, visuals, or proof. A final slide with a clear next step. Short native videos under 60 seconds with subtitles. The hook must land in the first two to four seconds. Walkthrough and behind-the-scenes videos continue outperforming polished talking-head content when the information is concrete and tactical. What is underperforming: Link posts with no setup. Metrics with no narrative. Large, dense text blocks. Generic advice that applies to everyone. Posts where the author disappears after publishing and does not reply in the first hour. My engagement strategy: Comment on 20 to 30 posts per day with insight tied directly to the post. Like 50 or more posts per day. Reply to every comment on your own posts within the first hour. DM five to ten people per day with context-first value tied to something they posted. Ask follow-up questions inside comment threads to deepen discussion. Repeated engagement from the same people increases future distribution. Hooks performing best right now: “I started this account 65 weeks ago. Here is what $340,000 in LinkedIn revenue actually looks like.” “This 4-slide carousel booked 5 calls in 24 hours.” “If I had to rebuild my LinkedIn from zero today, this is the exact system I would use.” “My 3-post-per-day routine for consistent inbound.” “I made X this month from LinkedIn. Here is the breakdown.” Every hook must be backed by proof. Without proof, credibility drops fast. Here is a 30-day plan that still works: Post three times per day with at least one proof-based post. Comment on 20 to 30 posts daily with substance. Like 50 or more posts per day. Reply to every comment within the first hour. Repost one winner each week with a new angle. DM five to ten people per day with context-first value. Track impressions, comment depth, leads, and repeating commenters weekly. Test hooks, formats, and timing every week. Run this system for 30 days. Screenshot your Day 31 results. Tag me when inbound starts. If you want the full cheat sheet, follow me, repost this, and reply “LinkedIn Growth Guide.” You must do all 3 to receive the DM.

She literally tells how to create a frequency so magnetic your desires chase you.

@openclaw Excellent. Looks like the team are seeing discord.

how to set up live Chrome sessions: 1️⃣ open chrome://inspect/#remote-debugging 2️⃣ toggle it on 3️⃣ that's it. your agent can now see your tabs, cookies, logins — everything uses Chrome DevTools MCP under the hood, no extensions needed 📖 developer.chrome.com/blog/chrome-de… 📖 #chrome-existing-session-via-mcp" target="_blank" rel="nofollow noopener">docs.openclaw.ai/tools/browser#…

OpenClaw 2026.3.13 🦞 👁️ live Chrome session attach — real logins, one toggle, zero extensions 📱 android redesigned & down to 7MB, iOS gets welcome pager 🐳 docker timezone override 🪟 windows gateway tweaks the lobster sees all now github.com/openclaw/openc…