Ayush 🦞

Unlocked a crazy use case with Nano Banana Pro. Take your complex papers, in this case I fed all the research I had done for Meta Ads and Andromeda update in 2025. And use this prompt: Take this paper and transform it into the image of a professor whiteboard image. Diagrams, arrows, boxes, and captions explaining the core idea visually, use colors as well. P.S - You can unlock unlimited Nanobanana Pro with @higgsfield_ai this week.

@leojrr Can't wait!

still sending Anything credits to everyone who follows our IG reply here if i missed you

@leojrr Long time supporter. Just followed on IG too.

we want more followers on IG i'm dropping Anything credits to everyone who follows us could be 5k could be 100k reply if you want some

@mikefutia Claude

Claude Code can now watch & analyze ANY video 🤯 I built a skill that gives Claude the ability to watch any video file you drop in — UGC ads, competitor Meta ads, organic TikToks, screen recordings, anything. All inside Claude Code. Perfect for DTC brands and agencies who study competitor creative every week to figure out what's working and what to test next. Here's the problem: If you're studying competitor ads on Meta or hooks on TikTok, you're scrubbing through videos manually, pausing to write down hooks, screenshotting on-screen text, and trying to remember what made the ad land by the time you've watched 10 of them. This skill solves it: → Drop any video file into Claude Code → Skill routes it through the Gemini API for native video understanding → Returns a full creative teardown — hook breakdown, target audience, angle, beat-by-beat, on-screen text verbatim → Surfaces the steal-worthy patterns you can apply to your own creative → Same skill works on UGC ads, produced video ads, organic TikToks, and Loom recordings No manual scrubbing. No pausing every 5 seconds. No $200/mo ad intelligence platform. What you get: - Native video understanding via Gemini (not just transcripts) - Structured analysis — hook, angle, audience, pain point, CTA - Verbatim on-screen text and dialogue with timestamps - Hook variations generated directly from competitor ads - About 27 cents per 30-minute video Built 100% in Claude Code with the Gemini API. I recorded a full breakdown showing exactly how I built this and I'm giving away the skill for free. Want the skill? > Comment "CLAUDE" + > Like this post And I'll send it over (must be following so I can DM)

@higgsfield Finally!

Meet Higgsfield CLI + Marketing Skills. Instead of burning tokens on bloated schemas, or shipping broken creative at scale, the CLI keeps agent spend lean and Skills keep output high quality. Pairs with Сodex, Claude Code, Openclaw etc. npx skills add higgsfield-ai/skills

@pounddz Pep

Your literally missing out on the Peptide gold rush right now if your not an affiliating for them Affiliates are making $30k - $50k every month just creating AI UGC and generating traffic to them organically I figured out a method that crushes on TT and literally made these videos in 30 mins You create the viral transformational edit videos then pair them with podcast clips of the same avatar Both formulas are crushing right now I put my full process how I print with Peptide affiliate organically into a google doc if you want it RT this + Comment "pep" and I'll send you it (must be following so I can DM you)

@mitte_ai Great update.!

new mitte preset: web designer. → create premium website designs. → implement them easily. examples + link 👇🏼

@abouelatta_ali Sounds really cool. Gonna check it out!

I hated how bad agents are at design I hated how Codex can't access Mobbin So I created Lazyweb - 257k+ screens (apps/web) - 6 opinionated design research skills - 1 MCP (Claude/Codex) 100% Free...AI native...no rate limits...no subscriptions.. Enjoy (and tell a friend) 🫡

@ibexdream @midjourney Very cool

Midjourney Sref #135 [your prompt] --sref 2198543851 --profile 9vogvvf kjwjzf1 --v 8.1

3D Characters are taking over.

@aimikoda Dude this is really helpful. I’m going to try this out right away.!

It looks like these sketch-style storyboards work really well in Seedance 2.0. I'm going to stick with this approach for a while. In the video prompt, I only include intent, style, reference and visual approach. It follows the storyboard surprisingly well. I'm sharing below the GPT Image 2 prompt I use to create the previs, along with the video prompt I use afterwards. Created on @MartiniArt_

@thatroblennon Great to have you (semi) back Rob. I literally asked Grok where is Rob Lennon just a few days ago. Would love to learn about your agentic workflows. It’s been a crazy few months.

my work today looks nothing like it did 9 months ago haven't been creating content. been building this whole time. here's the update I just sent my list: --- 🟡 been a minute Been a minute since I emailed this list. The world’s still changing, so let’s talk about AI. It’s Saturday morning, and I’m sitting in my recliner by the glass doors in the back of the house, looking out at the plants in the backyard. I’ve written a few drafts of this email before. It always goes on too long, tries to cover too much. Because there’s so much to say. I haven’t been producing content, posting, emailing, any of that lately. For the second half of 2025 I’d started feeling like I’d said all I had to say, about prompting, automation, AI. If you know my worldview, you know I abhor the idea of content for content’s sake. Even if you create with the help of AI (which I've taught), you need to bring ‘the egg’… whatever it is that comes from you that makes the content interesting. Worth consuming. And I was feeling a bit like a University professor stereotype. Too much teaching. Not enough doing. Not enough building. So when my consulting opportunities reached a critical mass, I took the opportunity to go all in and start building again. Work on business problems outside of the meta creator-solopreneur world. Real stuff. Biggest of all is that I’ve been working a lot on AI agent harnesses, skills, tools, and apps that make it all make sense to the human in the driver seat. My POV on agents and skills has changed a lot. I’m now a fan (in most cases). At the same time, I’ve evolved into a software engineer. I still can barely write a lick of code by hand, but that doesn’t matter. And I say this not to brag, but to inspire (I hope). I’d say at this point I’m a 10x engineer. I have totally outpaced most of the traditional software engineers I interact with, even though they have access to the same tools. By the end of the year, I expect to be a 100x engineer. When you can’t look at the code and know whether it’s good, you have no choice but to build systems around it. That’s something I hope to teach at some point, but I’m still knee-deep in it right now. For coding harnesses, I use Codex as my main driver (via 2 x $200/month ChatGPT subscriptions) with Claude for a bunch of more specialized work (1 x $200/month). My setup evolves constantly, so it feels like there’s never a good moment to stop and say, “This is the way to do it,” but I am trying to at least capture a snapshot for you. Not just for coding. For *everything*. Almost anything I used to use Make or N8N for... or GPTs, prompts, all that stuff, it's now just *here* as skills and workflows and SOPs and Obsidian vaults (folders full of markdown text files) that connect to all of it. Real soon I hope to publish what I’m calling my Personal OS. I’m barely in the actual ChatGPT or Claude web chat anymore. I’m in this. Personal OS will be a snapshot of what I use daily. I'm trying to get it to set itself up for you depending on your needs and what you have already. It'll come with the business-focused skills and things and I think the coding stuff will be an optional upgrade. I’ve been working for weeks to turn this in this template that sets itself up, and a short 1-hour course about these agent harness things and how to use them to be a 10x or 100x of whatever you want to be. People have been asking for it, so I’m delivering. Here’s what my typical day looks like: After getting the kiddos off to school and the dog walked, I’m running Codex and Claude apps across two monitors, along with some Obsidian vaults and a few web browsers. I’ll be managing 3-5 workstreams at a time, with agents performing research, coding up new features, exploring ideas, managing my task list, checking my email, investigating bugs, building a little hobby app on the side… whatever I think they can do for me. Maybe 30% of the messages I send invoke one or more skills. This is where prompt engineering has evolved to, although a skill is often much more than a prompt. The two skills I use the most are called “Now what? Figure out a plan” and “Fresh eyes”. You can probably guess a little about what they do. So anything I do often becomes a skill, and it’s something I work with the agent to improve over time. Any time I use the skill and I don’t like how it went, I might update it. 95% of the time I tell the AI to update its own skill based on what I want. A by-hand pass over a skill often reveals ways to improve it, in minor ways, but usually it’s not necessary unless it’s a core file like your root AGENTS.md or CLAUDE.md files. Not everything can be AI-driven, obviously, so I'm regularly stopping, reviewing, planning, figuring stuff out. That can be the hardest transition, like going 100 mph on the freeway and having to suddenly get out of the car and start walking every once and a while. But it can be good to slow down and go outside sometimes, right? SO. Will I start creating content again regularly? It’s hard to say definitively. I love building and I’m hoping to continue that. But I’ve discovered so much, it feels wasteful not to share. So I’m trying to get back into it. This is a crazy moment in history. ​ What's possible today wasn't possible 6 months ago. ​ I’m doing everything I can to capture it. To play the role I want to play in it as best I can. But boy-oh-boy, even with 3 mega subscriptions and 5 agents running all day, I never can seem to get all the work done. But that’s maybe because I’m aiming for 10-100x bigger goals than I ever have before. Hope you’re well. ​ Cheers, Rob Lennon -- PS - Btw, if you’ve been into the OpenClaw hype, Claude and Codex do most of the useful stuff OpenClaw does, but way better imo. And with OpenAI acquiring OpenClaw, we’re seeing a lot of improvements hit Codex that make it not-just-for-coders anymore. PPS - This message was written 100% by a human with no AI involvement.

@pcshipp Meta all day.!

Hey devs, I’m ready to invest $500 in ads. Which platform is best for ROI? - Meta ads - Apple ads - Google ads - Tik Tok ads

@0xBrekai Love @mitte_ai

I was checking mitte.ai plans yesterday and got hit by the classic mobile misclick and bought the wrong one. Emailed Hana about it and they got back super fast and processed the refund. Honestly one of the best customer service experiences I’ve seen compared to other platforms. Big thanks to them 🤜🤛 @mitte_ai

@nikitabier Yes extremely

Would it valuable to know how many of your followers have been active on X in the last 24 hours?

@MrBeast .

If this tweet has exactly 1 like in 24 hours I’ll give that person $1,000,000

@astnkennedy Read books.!

I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless

@fivosaresti ABM

I’ve NEVER seen a B2B company fail to scale with ABM when they build signal infrastructure that automatically scores, routes, and alerts. That said... We just built this ABM playbook for you to steal. It’s the same playbook we deploy for clients that generate HUNDREDS of thousands in pipeline. 8 steps from ICP model to realtime CRM updates with intent signals and dedicated Slack channels for warm leads. Inside, this document, I break down the entire workflow: • The 8-step framework from ICP to activation • How we track 1st, 2nd, and 3rd party signals • The awareness scoring model (5 stages) • CRM automation structure • How Slack channels keep reps focused on warm leads Comment "ABM" and I'll DM it to you. (must be following)

@higgsfield @PrometheanAIX Excellent update.

Higgsfield Canvas is LIVE! 🧩 A node-based workspace for team brainstorming and repeatable content pipelines. Plan pre-production and chat directly inside the canvas. Use an agent-built workflow or craft your own.

@pcshipp yup

@FollowAurelius Ai answer queries?

Why does SEO feel so much harder now? - 0 clicks - 8.8 average position - 291 total impressions I’ve indexed 10K+ pages yet the results are still terrible

@aryanlabde $100 Claude

As a vibe coder, which plan gives you the best value right now? - $20 claude - $100 codex - $200 claude