Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🚨 UNLIMITED EVERYTHING for 30 days! From Oct 28–Dec 1, every Adobe Creative Cloud & Firefly subscriber unlocks: ✨ Unlimited access to Firefly & partner AI models (ChatGPT, Ideogram 3.0, nano banana, Flux, Firefly 5 and more). ✨ Even video generation is unlimited in Relax mode. No credits. No... show more

Umesh

46,454 subscribers

18,209 views • 8 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

Umesh

19,281 views • 6 months ago

Claude + Meta + GPT Image 2 = AI UGC FACTORY Here's the free workflow Real UGC creators charge $150-$500 per video. 5-7 day turnaround. By the time you get 12 variants, your winning angle is already dead. We built a system that does 12 unique video ads in under an hour. Cost per video? Less than your coffee. The stack: • HeyOz (product import + export hub) • Claude (creative director + prompt engine) • GPT Image 2 (photorealistic starting frames) • Seedance 2.0 (animation) Broke down the entire thing in a step-by-step guide. What you'll get: → The exact 5-step workflow from URL to finished ad → 3 copy-paste image prompts (Stanley Quencher example) → 3 matching motion prompts for Seedance → The prompt framework that fixes 90% of bad AI outputs → Why grip specificity is the make-or-break variable most people miss → The 70/30 strategy for scaling (AI for testing, humans for winners) No design skills needed. No Canva. No CapCut. No Adobe. Just paste your product URL. Generate. Export. Launch. If you're running Meta or TikTok ads and your creative rotation is slower than your ad spend, this is for you. Comment "factory" to get access (must be following)

Claude + Meta + GPT Image 2 = AI UGC FACTORY Here's the free workflow Real UGC creators charge $150-$500 per video. 5-7 day turnaround. By the time you get 12 variants, your winning angle is already dead. We built a system that does 12 unique video ads in under an hour. Cost per video? Less than your coffee. The stack: • HeyOz (product import + export hub) • Claude (creative director + prompt engine) • GPT Image 2 (photorealistic starting frames) • Seedance 2.0 (animation) Broke down the entire thing in a step-by-step guide. What you'll get: → The exact 5-step workflow from URL to finished ad → 3 copy-paste image prompts (Stanley Quencher example) → 3 matching motion prompts for Seedance → The prompt framework that fixes 90% of bad AI outputs → Why grip specificity is the make-or-break variable most people miss → The 70/30 strategy for scaling (AI for testing, humans for winners) No design skills needed. No Canva. No CapCut. No Adobe. Just paste your product URL. Generate. Export. Launch. If you're running Meta or TikTok ads and your creative rotation is slower than your ad spend, this is for you. Comment "factory" to get access (must be following)

HeyOz

43,163 views • 1 month ago

I just vibe coded a Meta Ads creative analytics tool in Claude Code 🤯 It plugs into your ad accounts, AI-analyzes every creative you've ever run, and tells you exactly what's working, what isn't, and WHY. Built 100% in Claude Code. Perfect for DTC brands and creative agencies who are sick of staring at Ads Manager trying to reverse-engineer why one ad scaled and another tanked. If you're pulling weekly reports that show you spend, ROAS, CTR, and hook rate but never tell you WHY any of it is happening — and you're stuck watching videos one by one, guessing at angles, and making kill/scale calls on gut feel... This tool runs the entire loop for you: → Connect your Meta ad accounts in one click → AI watches every video and analyzes every static → Auto-labels each ad by asset type, messaging angle, hook tactic, and funnel stage → Win rate analysis broken down by every category → Kill/scale recommendations segmented by TOF, MOF, and BOF → AI-generated iteration recommendations for every underperformer No manual video watching. No guessing at what's working. No spreadsheets to track creative performance. What you get: - A full creative analytics dashboard pulling live from your accounts - AI classification on every ad you've ever run - Iteration priorities ranked by ads with real spend behind them - Weekly reports surfacing top and bottom performers with AI insights Built 100% in Claude Code as a real tool, not a one-off script. I recorded a full walkthrough showing exactly how this works and what every feature does, including ALL the prompts I used so you can build it yourself. Want access to all the prompts for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just vibe coded a Meta Ads creative analytics tool in Claude Code 🤯 It plugs into your ad accounts, AI-analyzes every creative you've ever run, and tells you exactly what's working, what isn't, and WHY. Built 100% in Claude Code. Perfect for DTC brands and creative agencies who are sick of staring at Ads Manager trying to reverse-engineer why one ad scaled and another tanked. If you're pulling weekly reports that show you spend, ROAS, CTR, and hook rate but never tell you WHY any of it is happening — and you're stuck watching videos one by one, guessing at angles, and making kill/scale calls on gut feel... This tool runs the entire loop for you: → Connect your Meta ad accounts in one click → AI watches every video and analyzes every static → Auto-labels each ad by asset type, messaging angle, hook tactic, and funnel stage → Win rate analysis broken down by every category → Kill/scale recommendations segmented by TOF, MOF, and BOF → AI-generated iteration recommendations for every underperformer No manual video watching. No guessing at what's working. No spreadsheets to track creative performance. What you get: - A full creative analytics dashboard pulling live from your accounts - AI classification on every ad you've ever run - Iteration priorities ranked by ads with real spend behind them - Weekly reports surfacing top and bottom performers with AI insights Built 100% in Claude Code as a real tool, not a one-off script. I recorded a full walkthrough showing exactly how this works and what every feature does, including ALL the prompts I used so you can build it yourself. Want access to all the prompts for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

54,648 views • 2 months ago

Sora 2 + n8n is absolutely insane 🤯 This n8n automation generates entire UGC campaigns with the same AI creator across unlimited videos. All from one Airtable form. Perfect for DTC brands & agencies who need brand consistency in their AI ads without hiring real creators. Why this matters: Every AI video tool gives you a random person each time. You can't build multi-video campaigns because your "creator" changes in every clip. Sora 2 consistent characters solves this: Same AI creator → Different scenes → Unlimited videos The n8n workflow: → Fill out Airtable form once (select your character, describe scenes, choose quantity) → Claude AI generates professional Sora 2 prompts automatically → Sora 2 renders videos with your consistent character → Videos auto-upload to ImageKit CDN → Everything tracked in Airtable with shareable URLs No manual prompting. No file management. No different people in every video. What you can create: → 3-part testimonial series with the same person → Before/during/after transformation campaigns → Product tutorial sequences that feel cohesive → Entire ad creative libraries with your "brand ambassador" Track everything in Airtable: → Video status (queued → generating → complete) → Shareable URLs for each clip → Scene descriptions and prompts → Production-ready in 5-10 minutes Built 100% in n8n + Airtable. Want the complete template? > Comment "SORA" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

18,972 views • 8 months ago

Claude Cowork + Meta Ads is absolutely wild 🤯 I built an AI creative system that does what most ad teams can't. Every AI model I tested fell flat on ad creative. Generic hooks, surface-level angles, zero understanding of what actually converts on Meta. Then I got inside Claude Cowork. 12 hours later I had a full system dialed in for paid social creative. Here's what it does: → Analyzes your best ads and tells you exactly why they're winning → Generates fresh angles segmented by buyer awareness level → Writes first lines engineered to stop the scroll on Meta → Builds execution-ready briefs your creative team can run with immediately → Flags when your current ads are going stale and suggests pivots All inside one Claude Cowork workspace. No plugins. No extra tools. Here's who this is for: Brands spending $50K-$500K/month on Meta who are stuck in the same cycle: -> Your creative team keeps testing random ideas -> Your winners eventually die and the replacement process is slow -> Nobody can produce volume fast enough to keep up with the algorithm This system turns a week of creative strategy into a single afternoon. I packaged the whole thing into 50 ready-to-use prompts across 5 categories: -> Winning Ad Analysis -> Angle Generation -> Scroll-Stop Hooks -> Creative Brief Builder -> Ad Refresh & Fatigue Prevention Copy, paste, run. Want access for free? > Like this post > Comment "COWORK" And I'll send it over (must be following so I can DM)

Claude Cowork + Meta Ads is absolutely wild 🤯 I built an AI creative system that does what most ad teams can't. Every AI model I tested fell flat on ad creative. Generic hooks, surface-level angles, zero understanding of what actually converts on Meta. Then I got inside Claude Cowork. 12 hours later I had a full system dialed in for paid social creative. Here's what it does: → Analyzes your best ads and tells you exactly why they're winning → Generates fresh angles segmented by buyer awareness level → Writes first lines engineered to stop the scroll on Meta → Builds execution-ready briefs your creative team can run with immediately → Flags when your current ads are going stale and suggests pivots All inside one Claude Cowork workspace. No plugins. No extra tools. Here's who this is for: Brands spending $50K-$500K/month on Meta who are stuck in the same cycle: -> Your creative team keeps testing random ideas -> Your winners eventually die and the replacement process is slow -> Nobody can produce volume fast enough to keep up with the algorithm This system turns a week of creative strategy into a single afternoon. I packaged the whole thing into 50 ready-to-use prompts across 5 categories: -> Winning Ad Analysis -> Angle Generation -> Scroll-Stop Hooks -> Creative Brief Builder -> Ad Refresh & Fatigue Prevention Copy, paste, run. Want access for free? > Like this post > Comment "COWORK" And I'll send it over (must be following so I can DM)

Mike Futia

85,465 views • 4 months ago

🚨 JUST IN: THIS FREE TOOL JUST REPLACED FOUR AI IMAGE AND VIDEO SUBSCRIPTIONS AT ONCE. Midjourney. Krea. Higgsfield. Openart. One repo. 200+ models. Zero dollars a month. Here is what it actually does. It is a full image and video studio that runs in your browser or as a desktop app. Text to image, image to image, text to video, image to video, lip sync, cinema mode with real camera controls. All of it. 4,500 people already starred this. What you get for free: → 50+ image models including Flux, Midjourney v7, Ideogram, GPT-4o, Seedream → 60+ video models including Kling, Sora, Veo, Runway, Wan, Hailuo → lip sync studio with 9 dedicated models. upload a portrait and audio and it talks → cinema studio with real camera controls. lens, focal length, aperture, film stock → feed up to 14 reference images into one generation → self-hosted. your data never leaves your machine The crazy part is there is also a hosted version that needs zero setup. Just open the link and start generating. Now the math. Midjourney Standard: $30/month Krea AI Pro: $30/month Higgsfield Plus: $49/month Openart AI: $15/month That is $124 a month. $1,488 a year. This repo does everything all four do. With more models than any of them. For free. Forever. No subscription. No vendor lock-in. MIT licensed. Download it in one click on Mac or Windows. Someone should have told me about this sooner. I feel like an idiot. ( save this )

🚨 JUST IN: THIS FREE TOOL JUST REPLACED FOUR AI IMAGE AND VIDEO SUBSCRIPTIONS AT ONCE. Midjourney. Krea. Higgsfield. Openart. One repo. 200+ models. Zero dollars a month. Here is what it actually does. It is a full image and video studio that runs in your browser or as a desktop app. Text to image, image to image, text to video, image to video, lip sync, cinema mode with real camera controls. All of it. 4,500 people already starred this. What you get for free: → 50+ image models including Flux, Midjourney v7, Ideogram, GPT-4o, Seedream → 60+ video models including Kling, Sora, Veo, Runway, Wan, Hailuo → lip sync studio with 9 dedicated models. upload a portrait and audio and it talks → cinema studio with real camera controls. lens, focal length, aperture, film stock → feed up to 14 reference images into one generation → self-hosted. your data never leaves your machine The crazy part is there is also a hosted version that needs zero setup. Just open the link and start generating. Now the math. Midjourney Standard: $30/month Krea AI Pro: $30/month Higgsfield Plus: $49/month Openart AI: $15/month That is $124 a month. $1,488 a year. This repo does everything all four do. With more models than any of them. For free. Forever. No subscription. No vendor lock-in. MIT licensed. Download it in one click on Mac or Windows. Someone should have told me about this sooner. I feel like an idiot. ( save this )

Kanika

14,737 views • 2 months ago

I just vibe-coded a Shopify Reviews Scraper that swipes all your competitors' customer reviews instantly. 🤯 Paste any competitor's product URL → pull every review in under 30 seconds → export to CSV. Built 100% in Codex. Perfect for brands and agencies who want to mine competitor voice-of-customer data at scale and turn it into winning ad creative. Here's how it works: → Drop a Shopify product URL into the tool → Set your review limit (50, 100, 500+) → Hit scrape — it launches a browser, finds the review widget, pulls every review → Export clean rows: rating, body, author, date → Feed the CSV to Claude and ask "what do customers love and hate about this product" → Turn the output into ad angles, hooks, and headlines No more paying $99/mo for clunky review scraping SaaS that locks you behind credits. What you get: - Any Shopify store's reviews in 30 seconds - Clean structured data (rating, body, author, date) - CSV or JSON export — drops straight into Sheets or an LLM - Unlimited scrapes, no per-review fees - A voice-of-customer firehose you can turn into ad creative on demand This is essentially a competitor review intelligence engine in a box. I'm giving away the full GitHub repo so you can clone it and run it yourself for free. Want the repo? > Like this post > Comment "SCRAPE" And I'll send it over (must be following so I can DM)

I just vibe-coded a Shopify Reviews Scraper that swipes all your competitors' customer reviews instantly. 🤯 Paste any competitor's product URL → pull every review in under 30 seconds → export to CSV. Built 100% in Codex. Perfect for brands and agencies who want to mine competitor voice-of-customer data at scale and turn it into winning ad creative. Here's how it works: → Drop a Shopify product URL into the tool → Set your review limit (50, 100, 500+) → Hit scrape — it launches a browser, finds the review widget, pulls every review → Export clean rows: rating, body, author, date → Feed the CSV to Claude and ask "what do customers love and hate about this product" → Turn the output into ad angles, hooks, and headlines No more paying $99/mo for clunky review scraping SaaS that locks you behind credits. What you get: - Any Shopify store's reviews in 30 seconds - Clean structured data (rating, body, author, date) - CSV or JSON export — drops straight into Sheets or an LLM - Unlimited scrapes, no per-review fees - A voice-of-customer firehose you can turn into ad creative on demand This is essentially a competitor review intelligence engine in a box. I'm giving away the full GitHub repo so you can clone it and run it yourself for free. Want the repo? > Like this post > Comment "SCRAPE" And I'll send it over (must be following so I can DM)

Mike Futia

29,760 views • 2 months ago

The era of the specialist is over. Full-stack GTM athletes are taking over. For too long, GTM has been divided into specialists, creating a soul-crushing web of dependencies: - Sales needs a custom business case to close a deal, but Marketing is slammed. - Marketing has a winning campaign idea, but design and engineering can’t prioritize it. - CRO has 5 ideas for increasing sales productivity, but no GTM engineers to execute. In GTM, speed is everything and dependencies are the enemy. That's why we're giving GTM teams the full-stack capabilities they need to close revenue. Welcome to the era of the GTM Athlete. These are people who don't ask permission or wait in queues. They can do whatever is needed to take deals from cold to closed—research accounts, launch ads, create a business case, generate tailored follow-ups, and close deals. Sales rep brainstorms with their champion how to convince the CISO. 30 mins later sends them a polished business case with security architecture and ROI. By lunch time, she launches ads to the entire buying committee. The next day, the rep presents a custom deck to key decision makers and gets verbal commitment. No more begging. No more waiting. No more losing. Our vision is to build the AI Swiss Army knife that turns specialists into GTM athletes. Today we are launching a critical capability that enables this vision: an AI agent that can create anything customer facing. You can now create executive business cases, deal follow-ups, landing pages, ABM campaigns and more, all by yourself. Unlike other AI tools, our agent plugs into your brand and data to create materials that actually look and sound like you. Sign up on our website. We're letting people off the waitlist every day, with 30 days of unlimited AI usage. I’d love to hear your feedback.

Jaleh Rezaei

219,240 views • 5 months ago

So Cluely is getting 400k+ views with AI TikTok slideshows. And I just automated the entire system 🤯 AI selfie hook → listicle slides → soft CTA on the last slide. Rinse. Repeat. Scale. And now my n8n + Airtable system runs it on complete autopilot. Perfect for e-comm brands & SaaS companies who want to test this format without the manual grind. Here's why this format is blowing up: → AI-generated "selfie" as the hook image → 5-8 slides with tips, hacks, or advice → Text overlays generated automatically → Promotes product on the final slide → Music added automatically on publish 362k views. 462k views. 492k views. Same playbook, multiple accounts, fully automated. Here's what my system does: → Define your niche, tone, and content style in Airtable → AI generates slide text and hooks automatically → Nano Banana creates every image with text overlays → Preview and approve before anything goes live → Blotato publishes to TikTok on your schedule—with music No manual Canva work. No writing slides one by one. No posting by hand. What you control in Airtable: * Niche and content direction * Hook style and tone * Image aesthetic and reference images * Posting schedule (days + times) * Approval before publish Set it up once. Let it run daily. I recorded a full step-by-step tutorial showing exactly how to build this system. Want access for free? > Like this post > Comment "SLIDES" And I'll send it over (must be following so I can DM)

So Cluely is getting 400k+ views with AI TikTok slideshows. And I just automated the entire system 🤯 AI selfie hook → listicle slides → soft CTA on the last slide. Rinse. Repeat. Scale. And now my n8n + Airtable system runs it on complete autopilot. Perfect for e-comm brands & SaaS companies who want to test this format without the manual grind. Here's why this format is blowing up: → AI-generated "selfie" as the hook image → 5-8 slides with tips, hacks, or advice → Text overlays generated automatically → Promotes product on the final slide → Music added automatically on publish 362k views. 462k views. 492k views. Same playbook, multiple accounts, fully automated. Here's what my system does: → Define your niche, tone, and content style in Airtable → AI generates slide text and hooks automatically → Nano Banana creates every image with text overlays → Preview and approve before anything goes live → Blotato publishes to TikTok on your schedule—with music No manual Canva work. No writing slides one by one. No posting by hand. What you control in Airtable: * Niche and content direction * Hook style and tone * Image aesthetic and reference images * Posting schedule (days + times) * Approval before publish Set it up once. Let it run daily. I recorded a full step-by-step tutorial showing exactly how to build this system. Want access for free? > Like this post > Comment "SLIDES" And I'll send it over (must be following so I can DM)

Mike Futia

181,303 views • 5 months ago

Google Gemini Omni is f*cking insane for UGC ads 🤯 Google just dropped their new video model and I spent the past 24 hours putting it through its paces. Multi-shot UGC ads -> Consistent creator across every scene ->Agent mode that runs the whole session. Perfect for DTC brands and agencies who need UGC creative at volume without hiring creators or paying per-video platform fees. If you're briefing creators every week, waiting days for footage, paying $150–$300 per UGC video, and still getting ads that miss the brand vibe... Gemini Omni eliminates the entire loop: → Generate a realistic AI creator from a single image prompt → Upload your creator + product image, reference both by filename in every prompt → Agent mode writes and runs your full production session → Creator stays consistent across every scene change and outfit → Product label accurate, correct color, readable text → 5-shot direct response ad in one briefing No creator briefs. No waiting for footage. No per-video platform fees. What you get: → Multi-shot UGC ads with a locked creator across every scene → AI creator image prompt tuned for realism — not plastic AI faces → Asset tagging system that keeps your product consistent shot to shot → A reusable workflow: new product, new angle, same pipeline I also built a Claude Cowork skill that writes your entire production package before you generate a single frame: Creator prompt, shot list, dialogue, asset-tagged prompts, and voiceover script. I put together a full playbook with the Claude skill file and the exact workflow to run this yourself. Want access for free? > Like this post > Comment "OMNI" And I'll send it over (must be following so I can DM)

Mike Futia

33,514 views • 1 month ago

💋 Darling, this isn’t another creator platform begging for scraps from the usual gatekeepers… this is a full-on power play. Welcome to the Bad Barbie Creator Platform — where the rules are written by us, the profits stay with us, and the vibe is unapologetically iconic. Here’s what actually matters: ✅ You own 100% of your content No algorithms throttling you. No sudden demonetization. No platform taking 30-50% forever. Your photos, videos, live streams, exclusive drops — yours, truly. ✅ Get paid instantly in crypto Tips, subscriptions, PPV — straight to your wallet the second they hit. No waiting 30 days, no “processing fees,” no excuses. USDT, ETH, SOL, whatever you want. ✅ Barbie holders get VIP treatment Hold $BADBARBIE tokens → automatic discounts on every creator’s page, early access to drops, and real governance power. The more you hold, the cheaper (and hotter) it gets. ✅ Community-owned & governed This isn’t some VC-funded cash grab. The platform belongs to the Barbie community. Token holders vote on features, fees, new tools, even which creators get boosted. Real Web3, not the fake “decentralized” marketing fluff. ✅ Built for the bold Uncensored (as long as it’s legal), high-vibe, luxurious. Whether you’re dripping in designer or dripping in desire — this is your empire, built your way. The era of begging platforms for crumbs is over. Step into the empire you were always meant to rule. 👑 Launching now at Get your $BADBARBIE tokens. Lock in your spot. Start collecting. #BadBarbie #Crypto #Web3 #CreatorEconomy #OwnYourEmpire #GirlsRunWeb3 #BarbieArmy

💋 Darling, this isn’t another creator platform begging for scraps from the usual gatekeepers… this is a full-on power play. Welcome to the Bad Barbie Creator Platform — where the rules are written by us, the profits stay with us, and the vibe is unapologetically iconic. Here’s what actually matters: ✅ You own 100% of your content No algorithms throttling you. No sudden demonetization. No platform taking 30-50% forever. Your photos, videos, live streams, exclusive drops — yours, truly. ✅ Get paid instantly in crypto Tips, subscriptions, PPV — straight to your wallet the second they hit. No waiting 30 days, no “processing fees,” no excuses. USDT, ETH, SOL, whatever you want. ✅ Barbie holders get VIP treatment Hold $BADBARBIE tokens → automatic discounts on every creator’s page, early access to drops, and real governance power. The more you hold, the cheaper (and hotter) it gets. ✅ Community-owned & governed This isn’t some VC-funded cash grab. The platform belongs to the Barbie community. Token holders vote on features, fees, new tools, even which creators get boosted. Real Web3, not the fake “decentralized” marketing fluff. ✅ Built for the bold Uncensored (as long as it’s legal), high-vibe, luxurious. Whether you’re dripping in designer or dripping in desire — this is your empire, built your way. The era of begging platforms for crumbs is over. Step into the empire you were always meant to rule. 👑 Launching now at Get your $BADBARBIE tokens. Lock in your spot. Start collecting. #BadBarbie #Crypto #Web3 #CreatorEconomy #OwnYourEmpire #GirlsRunWeb3 #BarbieArmy

Be Iconic

26,655 views • 7 months ago

LEARN SPANISH QUICK huevones I think I have some credibility here, here’s some vids from my IG narrating at one of my jobsites; I run my company comms entirely in Spanish and probably speak an equal amount of English/Spanish in my day to day. I’m terrible compared to a native speaker but better than most gringos Here are some things that helped/help me, YMMV 1. Get your head right: -you have to adopt an extreme beginner’s mindset and be okay feeling and sounding like an idiot. You can’t learn without putting yourself out there, you won’t be able to rewire your brain otherwise 2. Related to point 1 - humor helps A TON. If you’re going to sound like an idiot, lean into it - you want people to bust your balls. Learn to joke and make people laugh (learning swear words and local idioms is a great way to do this) 3. Make it clear you want and welcome correction. Make it safe for people to make fun of you, repeatedly ask for feedback (“soy gringo menso, ayúdame por favor 🙏🏻”) 4. Once you lay that groundwork, here’s your first cheat code: pick a book like Harry Potter (something with a lot of dialogue) and get the physical book and audiobook. Carve out 15-30 mins/day to do the following: listen to 2-3 sentences, and then read the same segment OUT LOUD (en voz alta) and repeat. You’ll get a sense for where your accent needs tweaking. Pay attention to how your mouth feels: what shape does it take, what physical space do the words occupy etc, Do this every day, no excuses, no off days. Repetition breeds familiarity. 5. Find a practice buddy - if you’re single, dating apps are great for this (don’t cancel me for this, there’s no greater forcing function to modify behavior than romance) or if that’s not for you, use an online service to find a convo buddy (via WhatsApp/facetime). Again, you gotta put yourself out there and be ok sounding/feeling dumb. 6. Do an English “fast” and put yourself in an environment with lots of speaking opportunities (eg take a 1 week vacation to CDMX and sign up for a bunch of tours and events away from English speakers). 1 week minimum, ideally 2. No English means no English. No calling or texting back home and breaking your fast. That’ll get you started. You can’t learn to speak without speaking. Reading and listening, IMO, sit in a far distant second place in the learning hierarchy Other stuff that wasn’t around when I started learning but that seems promising to me: 1. Duolingo - just kidding, this doesn’t seem to help anyone 2. Instagram accounts - like Maddie’s Mundo - for me the key here would be verbally repeating the stuff you see in the videos, NOT passively consuming them. Just like the audiobook hack: watch a video, verbally mimic it, watch again, copy it again, repeat repeat repeat 3. AI - I’m seeing some AI products that seem to allow you to have interactive verbal conversations. Seems very promising I’ll post some links and stuff below. Any other tips? (Duolingo owl, please don’t come for me,” or my family, I harbor no ill feelings toward you)

LEARN SPANISH QUICK huevones I think I have some credibility here, here’s some vids from my IG narrating at one of my jobsites; I run my company comms entirely in Spanish and probably speak an equal amount of English/Spanish in my day to day. I’m terrible compared to a native speaker but better than most gringos Here are some things that helped/help me, YMMV 1. Get your head right: -you have to adopt an extreme beginner’s mindset and be okay feeling and sounding like an idiot. You can’t learn without putting yourself out there, you won’t be able to rewire your brain otherwise 2. Related to point 1 - humor helps A TON. If you’re going to sound like an idiot, lean into it - you want people to bust your balls. Learn to joke and make people laugh (learning swear words and local idioms is a great way to do this) 3. Make it clear you want and welcome correction. Make it safe for people to make fun of you, repeatedly ask for feedback (“soy gringo menso, ayúdame por favor 🙏🏻”) 4. Once you lay that groundwork, here’s your first cheat code: pick a book like Harry Potter (something with a lot of dialogue) and get the physical book and audiobook. Carve out 15-30 mins/day to do the following: listen to 2-3 sentences, and then read the same segment OUT LOUD (en voz alta) and repeat. You’ll get a sense for where your accent needs tweaking. Pay attention to how your mouth feels: what shape does it take, what physical space do the words occupy etc, Do this every day, no excuses, no off days. Repetition breeds familiarity. 5. Find a practice buddy - if you’re single, dating apps are great for this (don’t cancel me for this, there’s no greater forcing function to modify behavior than romance) or if that’s not for you, use an online service to find a convo buddy (via WhatsApp/facetime). Again, you gotta put yourself out there and be ok sounding/feeling dumb. 6. Do an English “fast” and put yourself in an environment with lots of speaking opportunities (eg take a 1 week vacation to CDMX and sign up for a bunch of tours and events away from English speakers). 1 week minimum, ideally 2. No English means no English. No calling or texting back home and breaking your fast. That’ll get you started. You can’t learn to speak without speaking. Reading and listening, IMO, sit in a far distant second place in the learning hierarchy Other stuff that wasn’t around when I started learning but that seems promising to me: 1. Duolingo - just kidding, this doesn’t seem to help anyone 2. Instagram accounts - like Maddie’s Mundo - for me the key here would be verbally repeating the stuff you see in the videos, NOT passively consuming them. Just like the audiobook hack: watch a video, verbally mimic it, watch again, copy it again, repeat repeat repeat 3. AI - I’m seeing some AI products that seem to allow you to have interactive verbal conversations. Seems very promising I’ll post some links and stuff below. Any other tips? (Duolingo owl, please don’t come for me,” or my family, I harbor no ill feelings toward you)

jameson (big deck energy)

24,578 views • 1 year ago

Real Benefits of Staying Overnight at Accor’s Mercure Ba Na Hills 🏰☁️ Save Time • Save Money • Experience the REAL Ba Na Hills If Ba Na Hills, Vietnam 🇻🇳 is on your itinerary, do NOT do it as a day trip. An overnight stay at Mercure Ba Na Hills French Village completely changes the experience — and most people miss this 👇 ⸻ 🚡 World’s most unique hotel access — arrive by cable car with luggage This is the ONLY hotel where you reach your hotel room via cable car — with your luggage 🎒🧳 Your stay literally starts with a scenic cable car journey over the lush green forest, waterfalls and through the clouds ☁️ No roads. No buses. Just views and vibes. ⸻ ✨ Ba Na Hills at night = pure magic After sunset 🌄, it feels like you’re staying above the clouds ☁️ Silent streets, misty castles, and unreal vibes — something day visitors never see. 🚶‍♂️ Post 4:30 PM = Ba Na Hills becomes yours Once the day crowd leaves: • Empty streets • Quiet castles • Peaceful photo spots 📸 • Zero chaos ⸻ 🚡 VIP Cable Car access (Huge hidden benefit!) ✔️ Mercure guests get VIP / priority entry into cable cars ✔️ Private cable cars for your family only ✔️ No queues at all ⏳ Day visitors wait 60–90 minutes EACH side, and 10–15 people are packed into one cable car. This benefit alone saves hours. ⸻ 🎢 Fantasy Park with ZERO crowds 🗓️ Friday–Sunday: Open till 7 PM in the evening while day visitors leave by 4:30 PM. Unlimited FREE Rides, games, and 4D/5D shows — repeated multiple times 🎮🎠 No queues. No rush. Full fun mode 😍 ⸻ 🎿 Alpine Coaster Happy Hours = Double Win at this Gravity Based Roller Coasters 🎢, Most Popular at Ba Na 💰 Pay just VND 50k (instead of VND 80k) ⏰ 4:30–5:30 PM | 8:30–9:30 AM 🚫 Almost no waiting 🌫️ Evening mist rides on mountains = unforgettable ⸻ 🌉 Golden Hand Bridge — crowd-free access The iconic Golden Bridge is accessible ONLY to Mercure guests from 6 AM–8 AM Till ~9 AM, there are very few people — perfect for photos & serenity 📸 ⸻ 🚡 30% discount on Cable Car + ALL attractions if purchased at Mercure check-in, The two-way Cable Car tickets includes 👇following on all days on your Stay ✔️ All cable cars (up, down & internal) ✔️ All funiculars 🚆 ✔️ Unlimited Fantasy Park & Moon Castle games ✔️ 4D / 5D / 7D & 360° movies ✔️ Flying Eye Theatre ✔️ Indoor & outdoor bumper cars ✔️ All rides ✔️ Sun Castle & Moon/Lunar Castle ✔️ Le Jardin D’Amour, Pagoda & Love Garden 🌸 ✔️ Thác Thần Mặt Trời waterfall & Golden Horse Statue ✔️Except Alpine Coasters & 10D Show, everything is Free, unlimited times 🤩 Most day visitors don’t even realise what they miss. ⸻ 💡 Bottom Line: Ba Na Hills is NOT meant to be rushed. You need time to feel the vibe and explore peacefully. After staying there, I honestly wished I had booked 2 nights instead of 1. 🏰 A night stay at Mercure Ba Na Hills isn’t just about the hotel — it unlocks the best version of Ba Na Hills. 🔖 Save this post 🇻🇳 Stay tuned for more Vietnam travel & credit-card-optimised travel tips. 📘 Visit SpendWisely Blog: Detailed credit card reviews & guides 👉 Some links may be referral links in the above post. It supports the page without any cost to you. #creditcard #spendwisely #creditcards

Real Benefits of Staying Overnight at Accor’s Mercure Ba Na Hills 🏰☁️ Save Time • Save Money • Experience the REAL Ba Na Hills If Ba Na Hills, Vietnam 🇻🇳 is on your itinerary, do NOT do it as a day trip. An overnight stay at Mercure Ba Na Hills French Village completely changes the experience — and most people miss this 👇 ⸻ 🚡 World’s most unique hotel access — arrive by cable car with luggage This is the ONLY hotel where you reach your hotel room via cable car — with your luggage 🎒🧳 Your stay literally starts with a scenic cable car journey over the lush green forest, waterfalls and through the clouds ☁️ No roads. No buses. Just views and vibes. ⸻ ✨ Ba Na Hills at night = pure magic After sunset 🌄, it feels like you’re staying above the clouds ☁️ Silent streets, misty castles, and unreal vibes — something day visitors never see. 🚶‍♂️ Post 4:30 PM = Ba Na Hills becomes yours Once the day crowd leaves: • Empty streets • Quiet castles • Peaceful photo spots 📸 • Zero chaos ⸻ 🚡 VIP Cable Car access (Huge hidden benefit!) ✔️ Mercure guests get VIP / priority entry into cable cars ✔️ Private cable cars for your family only ✔️ No queues at all ⏳ Day visitors wait 60–90 minutes EACH side, and 10–15 people are packed into one cable car. This benefit alone saves hours. ⸻ 🎢 Fantasy Park with ZERO crowds 🗓️ Friday–Sunday: Open till 7 PM in the evening while day visitors leave by 4:30 PM. Unlimited FREE Rides, games, and 4D/5D shows — repeated multiple times 🎮🎠 No queues. No rush. Full fun mode 😍 ⸻ 🎿 Alpine Coaster Happy Hours = Double Win at this Gravity Based Roller Coasters 🎢, Most Popular at Ba Na 💰 Pay just VND 50k (instead of VND 80k) ⏰ 4:30–5:30 PM | 8:30–9:30 AM 🚫 Almost no waiting 🌫️ Evening mist rides on mountains = unforgettable ⸻ 🌉 Golden Hand Bridge — crowd-free access The iconic Golden Bridge is accessible ONLY to Mercure guests from 6 AM–8 AM Till ~9 AM, there are very few people — perfect for photos & serenity 📸 ⸻ 🚡 30% discount on Cable Car + ALL attractions if purchased at Mercure check-in, The two-way Cable Car tickets includes 👇following on all days on your Stay ✔️ All cable cars (up, down & internal) ✔️ All funiculars 🚆 ✔️ Unlimited Fantasy Park & Moon Castle games ✔️ 4D / 5D / 7D & 360° movies ✔️ Flying Eye Theatre ✔️ Indoor & outdoor bumper cars ✔️ All rides ✔️ Sun Castle & Moon/Lunar Castle ✔️ Le Jardin D’Amour, Pagoda & Love Garden 🌸 ✔️ Thác Thần Mặt Trời waterfall & Golden Horse Statue ✔️Except Alpine Coasters & 10D Show, everything is Free, unlimited times 🤩 Most day visitors don’t even realise what they miss. ⸻ 💡 Bottom Line: Ba Na Hills is NOT meant to be rushed. You need time to feel the vibe and explore peacefully. After staying there, I honestly wished I had booked 2 nights instead of 1. 🏰 A night stay at Mercure Ba Na Hills isn’t just about the hotel — it unlocks the best version of Ba Na Hills. 🔖 Save this post 🇻🇳 Stay tuned for more Vietnam travel & credit-card-optimised travel tips. 📘 Visit SpendWisely Blog: Detailed credit card reviews & guides 👉 Some links may be referral links in the above post. It supports the page without any cost to you. #creditcard #spendwisely #creditcards

SpendWisely

29,433 views • 6 months ago

Introducing Pods Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL. A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management. There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own. Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live. What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data. - No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on. - Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online. - Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it. - Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using. Coming soon: - Pod federation: pods form alliances with other pods. - Marketplace: pods with spare capacity can sell inference to other pods.

Introducing Pods Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL. A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management. There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own. Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live. What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data. - No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on. - Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online. - Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it. - Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using. Coming soon: - Pod federation: pods form alliances with other pods. - Marketplace: pods with spare capacity can sell inference to other pods.

Varun

308,089 views • 3 months ago

Hills I will die on as someone who has coached high school football for over 29 years: 1. If you are not PASSIONATE about blessing, serving, and empowering those you are blessed to coach, this profession is not for you. 2. As much as we need to know our trade, getting to know (and to love), our players is far more important. 3. This is an INTENSE game, and it’ll never be “just a game”, but it IS a game. Remember that when you’re with your team, and more importantly, remember that when you’re with your family. 4. Just as we teach our athletes to “leave things better than they found them”, we need to leave our athletes better than they were when they first entered into our program. Never let a day pass without pouring into each and every individual. 5. Life is complicated enough, let’s not complicate the game in such a way that we take the joy of it away from others. In other words… Keep it simple. 6. Our words carry little (or NO), value, if we don’t practice what we preach. WE as coaches should be learning and growing each and every day, just as we expect our athletes to. 7. As much as we all want to win those championship rings for our athletes, make sure you don’t lose your wedding ring in the process. 8. The athlete that may be “difficult to reach/teach” (the one who may get on your last nerve more than you could ever imagine), is someone’s EVERYTHING. Get to know them as human beings, find out what motivates them, and do everything you can to help them to thrive. 9. Be where your feet are. Don’t fall into the trap of chasing logos and thinking that a higher division, a bigger school, or going from HS to college, or even college to the pros, is going to be more rewarding or fulfilling. 10. The legacy you leave as a coach will never be determined by your wins and losses, but by the lives you were able to change for the better!

Hills I will die on as someone who has coached high school football for over 29 years: 1. If you are not PASSIONATE about blessing, serving, and empowering those you are blessed to coach, this profession is not for you. 2. As much as we need to know our trade, getting to know (and to love), our players is far more important. 3. This is an INTENSE game, and it’ll never be “just a game”, but it IS a game. Remember that when you’re with your team, and more importantly, remember that when you’re with your family. 4. Just as we teach our athletes to “leave things better than they found them”, we need to leave our athletes better than they were when they first entered into our program. Never let a day pass without pouring into each and every individual. 5. Life is complicated enough, let’s not complicate the game in such a way that we take the joy of it away from others. In other words… Keep it simple. 6. Our words carry little (or NO), value, if we don’t practice what we preach. WE as coaches should be learning and growing each and every day, just as we expect our athletes to. 7. As much as we all want to win those championship rings for our athletes, make sure you don’t lose your wedding ring in the process. 8. The athlete that may be “difficult to reach/teach” (the one who may get on your last nerve more than you could ever imagine), is someone’s EVERYTHING. Get to know them as human beings, find out what motivates them, and do everything you can to help them to thrive. 9. Be where your feet are. Don’t fall into the trap of chasing logos and thinking that a higher division, a bigger school, or going from HS to college, or even college to the pros, is going to be more rewarding or fulfilling. 10. The legacy you leave as a coach will never be determined by your wins and losses, but by the lives you were able to change for the better!

Coach Hines 🇺🇸

57,639 views • 1 month ago

A day in the life of an 100,000+ acre farm. Meetings start at the shop at 4:30am. You get in your drill and head off to your designated seeding area. There is about a 70km radius of crops to seed from the main binyard. I always thought 4:30am was so awesome. Imagine having to get everyone on board to wake up at 4am daily to crush acres, it’s a feat in this day and age undoubtedly. It’s also a reason why few can compete against operations like this, pure savagery. Every team that seeds together gets a crew truck. Nothing pisses a tired crew off more than being late & chances are you are driving your own truck out to the seeder when you show up late. It has to run like clockwork to seed everything in a timely manner because you may lose some days to rain. Typically you would run as long as you can every single day. A 16 hour days are easy, it’s the back to back to back 18 or 20 hour days that are killers. I really enjoyed the long hours, I had started to track every one of my movements by acres. I knew on a perfect day I could do about 766 acres a day, but every turn I would deduct acres, stop to piss I would deduct acres, run out and grab supper I would deduct acres, fill the seeder I would deduct acres, check my runs I would deduct acres, fix my hoses I would deduct acres, I knew exactly how to bang out an awesome day and that usually meant no liquids after 10am so I didn’t have to stop to piss. Not everyone did this, in fact probably no one but me did this but I was obsessed with efficiency at the time. Seeding could last anywhere from 25 to 45 days depending. 2 of the seeding units were kept to finish sloughs, while the rest of the tractors were cleaned up, serviced and dropped back off at the JD dealership. 5 or 6 tractors were kept for grain carts to use at harvest but next seeding year all brand new JD tractors will be used, there is never used tractors used, the deadline is far too important and the dependability & warranty is crucial to complete seeding on time.

bu/ac

57,117 views • 1 year ago

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.

Oren Melamed

29,555 views • 6 months ago

My favorite AI workflow lately is my thought-to-post pipeline. I just go on walks, have a good content idea, ramble it, and have an optimized post in my writing style without typing. It's super simple: 1. Download an AI-powered voice dictation app to your phone (I use Wispr Flow) 2. Go on long walks and let ideas flow - when you get a good one, open Wispr Flow and ramble your thoughts (doesn't need to be perfect) 3. Notes auto-save. These become the core ideas for posts later 4. Open Claude and create a new Project called "Post generator" 5. Use this prompt: "I’m going to provide you with my own written material, and your task will be to understand and mimic its style. You'll start this exercise by saying "BEGIN.” After, I'll present an example text, to which you'll respond, "CONTINUE". The process will continue similarly with another piece of writing and then with further examples. I'll give you unlimited examples. Your response will only be "CONTINUE.” You're only permitted to change your response when I tell you "FINISHED". After this, you'll explore and understand the tone, style, and characteristics of my writing based on the samples I've given. Finally, I'll prompt you to craft a new piece of writing on a specified topic, emulating my distinctive writing style" 6. Now's the fun part: Go to Twitter Analytics and download your top posts (Premium → Analytics → Content → Download button) 7. Paste your best-performing tweets into Claude repeatedly until it says "FINISHED" 8. Take your voice notes, paste them into your trained Claude Project, prompt "make a post in my writing style" 9. Post is ready to go. Polish and edit slightly *if* needed. The AI is trained on how you actually write, not generic content. Your voice notes capture your real, raw thoughts without the friction of typing. I have my best ideas while walking. If I try to write them in my notes app mid-walk, I forget halfway through. Voice dictation captures everything as I ramble. Game changer for turning scattered thoughts into polished posts!

My favorite AI workflow lately is my thought-to-post pipeline. I just go on walks, have a good content idea, ramble it, and have an optimized post in my writing style without typing. It's super simple: 1. Download an AI-powered voice dictation app to your phone (I use Wispr Flow) 2. Go on long walks and let ideas flow - when you get a good one, open Wispr Flow and ramble your thoughts (doesn't need to be perfect) 3. Notes auto-save. These become the core ideas for posts later 4. Open Claude and create a new Project called "Post generator" 5. Use this prompt: "I’m going to provide you with my own written material, and your task will be to understand and mimic its style. You'll start this exercise by saying "BEGIN.” After, I'll present an example text, to which you'll respond, "CONTINUE". The process will continue similarly with another piece of writing and then with further examples. I'll give you unlimited examples. Your response will only be "CONTINUE.” You're only permitted to change your response when I tell you "FINISHED". After this, you'll explore and understand the tone, style, and characteristics of my writing based on the samples I've given. Finally, I'll prompt you to craft a new piece of writing on a specified topic, emulating my distinctive writing style" 6. Now's the fun part: Go to Twitter Analytics and download your top posts (Premium → Analytics → Content → Download button) 7. Paste your best-performing tweets into Claude repeatedly until it says "FINISHED" 8. Take your voice notes, paste them into your trained Claude Project, prompt "make a post in my writing style" 9. Post is ready to go. Polish and edit slightly if needed. The AI is trained on how you actually write, not generic content. Your voice notes capture your real, raw thoughts without the friction of typing. I have my best ideas while walking. If I try to write them in my notes app mid-walk, I forget halfway through. Voice dictation captures everything as I ramble. Game changer for turning scattered thoughts into polished posts!

Rowan Cheung

129,419 views • 9 months ago

Here’s to Shashwat Sachdev. Some collaborations go beyond work, they become deeply personal. Sha has been that for me. Not just the music composer of Dhurandhar but someone I see as a younger brother, someone I’ve shared chaos, silence, ideas and some of the most intense creative days with. What he’s done on this film still doesn’t feel real when I say it out loud. 9 songs in 9 days for Dhurandhar Part 1, with the entire BGM done in 6 days. And then Dhurandhar Part 2, 14 songs in 11 days, BGM in 3. At that speed, at that scale, with that kind of emotional depth and that kind of extraordinary quality, it’s beyond crazy. And what makes it even more unreal is how both the albums, released within a span of 3 months, reached top global charts, with almost every song being loved and celebrated, something that’s an absolute rarity for any film in the world. For almost 15 days, my house stopped being a house. It became a living, breathing studio. Every room had something going on, music in the living room, recordings in the bedrooms, writing in the balconies. Singers and musicians walking in and out endlessly. Days and nights just blending into each other. 21–22 hour stretches, no real sense of time, just a shared madness to get it right. And right at the center of all of it was Sha. Holding everything together. Creating, composing, guiding, reacting, evolving, all at once. There were days he was unwell, running on barely any sleep, dealing with health scares but he still showed up fully, without compromise, without slowing down. That kind of resilience is rare. Having the legendary Irshad Kamil Sir alongside, and a team that gave everything they had, pushed this into something even more special. Everyone went into absolute God mode. And through all that chaos, Magic (Sha’s better half) was the anchor, keeping things steady, holding the energy together when everything could have easily fallen apart. What makes Sha truly special is not just his talent. It’s his hunger. His refusal to settle. His instinct to keep digging until something feels honest. He doesn’t chase easy, he chases truth in every note. That kind of commitment doesn’t come from skill alone. It comes from love. Love to achieve God through music. And you can feel that love in every second of Dhurandhar. Always grateful. Always rooting for you. ❤️

Here’s to Shashwat Sachdev. Some collaborations go beyond work, they become deeply personal. Sha has been that for me. Not just the music composer of Dhurandhar but someone I see as a younger brother, someone I’ve shared chaos, silence, ideas and some of the most intense creative days with. What he’s done on this film still doesn’t feel real when I say it out loud. 9 songs in 9 days for Dhurandhar Part 1, with the entire BGM done in 6 days. And then Dhurandhar Part 2, 14 songs in 11 days, BGM in 3. At that speed, at that scale, with that kind of emotional depth and that kind of extraordinary quality, it’s beyond crazy. And what makes it even more unreal is how both the albums, released within a span of 3 months, reached top global charts, with almost every song being loved and celebrated, something that’s an absolute rarity for any film in the world. For almost 15 days, my house stopped being a house. It became a living, breathing studio. Every room had something going on, music in the living room, recordings in the bedrooms, writing in the balconies. Singers and musicians walking in and out endlessly. Days and nights just blending into each other. 21–22 hour stretches, no real sense of time, just a shared madness to get it right. And right at the center of all of it was Sha. Holding everything together. Creating, composing, guiding, reacting, evolving, all at once. There were days he was unwell, running on barely any sleep, dealing with health scares but he still showed up fully, without compromise, without slowing down. That kind of resilience is rare. Having the legendary Irshad Kamil Sir alongside, and a team that gave everything they had, pushed this into something even more special. Everyone went into absolute God mode. And through all that chaos, Magic (Sha’s better half) was the anchor, keeping things steady, holding the energy together when everything could have easily fallen apart. What makes Sha truly special is not just his talent. It’s his hunger. His refusal to settle. His instinct to keep digging until something feels honest. He doesn’t chase easy, he chases truth in every note. That kind of commitment doesn’t come from skill alone. It comes from love. Love to achieve God through music. And you can feel that love in every second of Dhurandhar. Always grateful. Always rooting for you. ❤️

Aditya Dhar

675,425 views • 3 months ago

Thank you Centre Pompidou Centre Pompidou, everyone who made Nature Manifesto happen, and all the people that took it in. We were happy to see the conversations that the use of AI in Nature Manifesto sparked !! Below is a message from Björk: ~~~ “ the flood of all things from AI is overwhelming !! i am super grateful for your concerns about it´s effects on the environment , it shows you care , are curious and have integrity . i am curious too , i would like to be more informed about the difference of "frugal" AI and the ones that do hugeenvironmental damage and want to be able to choose . i asked around and found out that both the visuals and the audio in our pompidou project were done with "frugal" AI . but i have a lot to learn . when we used some of the AI softwares to merge the animals voices to mine , some of the sounds were great but to be honest , the best blends of their voices and a human were done "manually" , me editing the sounds , choosing piece by piece , looking for personality , musicality and soul . with new technology , i try to use it as a tool to grow , not a crutch . for example when i used melodyne , i used it not for lazy voice progressions but spent even more time when using it . every note in every chord became intentionally more complex . ( for example choir in "thunderbolt" ) and hopefully stretched the potential more out , further than i would have in "normal analog" physical improvisations ... i felt with this new tool i could reach new places in my musical DNA , become MORE personal . more myself . in my opinion , this is how we will work in the future . humans can read emotions on an incredibly high scale . nature made us that way . if there is no soul in tomorrow's music made by AI it is because no-one put it there and we have to speak out and guard this as listeners . ( tbh there is a lot of soulless muzak on spotify already ... they don’t need any AI help for that ...) anything that is mass manufactured without the attention of creativity , is that way . AI or not so it is not about the tool it is what you do with it . " ~~~ The visuals for Nature Manifesto were crafted by the talented Sam Balfus, artificial intelligence being one of the multiple tools used in the process. The sound was produced in collaboration with artist Robin Meier and IRCAM IRCAM. IRCAM develops “frugal AI” capable of generating audio in real-time on local servers without a GPU, thus their models can f.ex. be embedded on tiny Raspberry Pi cards. We asked associate professor and researcher Philippe Esling to provide us with readings; Constance Douwe’s thesis “On the environmental impact of deep generative models for audio” and more, see links below. Nature Manifesto Immersive sound piece 3’40” (2024) 20 November to 9 December, 2024, Centre Pompidou, Paris. Presented as part of the forum “Biodiversity: Which culture for which future?” #ForumBiodiversité Concept and words by Björk & Aleph Music written and composed by Björk Curatorship: Chloé Siganos and Aleph Molinari Associate curator: Delphine Le Gatt Ircam Musical Computing: Robin Meier Wiratunga Sound engineer: Bergur Þórisson Animation: Sam Balfua Video editing: Santiago Molinari With activists: Camille Etienne, Claire Nouvian, Sigrun Perla Gísladóttir, Sæunn Júlía Sigurjónsdóttir, Titouan Pilliard, of BLOOM, Sustainable Ocean Alliance, and Ungir umhverfissinnar. In partnership with D&B Audio and Southby Productions. Reccommended resources :

Thank you Centre Pompidou Centre Pompidou, everyone who made Nature Manifesto happen, and all the people that took it in. We were happy to see the conversations that the use of AI in Nature Manifesto sparked !! Below is a message from Björk: ~ “ the flood of all things from AI is overwhelming !! i am super grateful for your concerns about it´s effects on the environment , it shows you care , are curious and have integrity . i am curious too , i would like to be more informed about the difference of "frugal" AI and the ones that do hugeenvironmental damage and want to be able to choose . i asked around and found out that both the visuals and the audio in our pompidou project were done with "frugal" AI . but i have a lot to learn . when we used some of the AI softwares to merge the animals voices to mine , some of the sounds were great but to be honest , the best blends of their voices and a human were done "manually" , me editing the sounds , choosing piece by piece , looking for personality , musicality and soul . with new technology , i try to use it as a tool to grow , not a crutch . for example when i used melodyne , i used it not for lazy voice progressions but spent even more time when using it . every note in every chord became intentionally more complex . ( for example choir in "thunderbolt" ) and hopefully stretched the potential more out , further than i would have in "normal analog" physical improvisations ... i felt with this new tool i could reach new places in my musical DNA , become MORE personal . more myself . in my opinion , this is how we will work in the future . humans can read emotions on an incredibly high scale . nature made us that way . if there is no soul in tomorrow's music made by AI it is because no-one put it there and we have to speak out and guard this as listeners . ( tbh there is a lot of soulless muzak on spotify already ... they don’t need any AI help for that ...) anything that is mass manufactured without the attention of creativity , is that way . AI or not so it is not about the tool it is what you do with it . " ~ The visuals for Nature Manifesto were crafted by the talented Sam Balfus, artificial intelligence being one of the multiple tools used in the process. The sound was produced in collaboration with artist Robin Meier and IRCAM IRCAM. IRCAM develops “frugal AI” capable of generating audio in real-time on local servers without a GPU, thus their models can f.ex. be embedded on tiny Raspberry Pi cards. We asked associate professor and researcher Philippe Esling to provide us with readings; Constance Douwe’s thesis “On the environmental impact of deep generative models for audio” and more, see links below. Nature Manifesto Immersive sound piece 3’40” (2024) 20 November to 9 December, 2024, Centre Pompidou, Paris. Presented as part of the forum “Biodiversity: Which culture for which future?” #ForumBiodiversité Concept and words by Björk & Aleph Music written and composed by Björk Curatorship: Chloé Siganos and Aleph Molinari Associate curator: Delphine Le Gatt Ircam Musical Computing: Robin Meier Wiratunga Sound engineer: Bergur Þórisson Animation: Sam Balfua Video editing: Santiago Molinari With activists: Camille Etienne, Claire Nouvian, Sigrun Perla Gísladóttir, Sæunn Júlía Sigurjónsdóttir, Titouan Pilliard, of BLOOM, Sustainable Ocean Alliance, and Ungir umhverfissinnar. In partnership with D&B Audio and Southby Productions. Reccommended resources :

björk

51,637 views • 1 year ago