issa bi

@mikefutia CLAUDE

Claude Code + Nano Banana 2 is f*cking cracked for advertorials 🤯 One prompt → a complete presell page with editorial copy, AI product photography, testimonials, and pricing — ready to paste into Shopify. Built 100% in Claude Code. Perfect for DTC brands and agencies running advertorials on Meta who need 5-10 different pages per month but can't keep paying $1,500 each. If you're briefing copywriters, waiting days for a draft, giving notes, waiting again, and still only getting one or two new pages per month... This system eliminates the entire loop: → Enter your brand, product, target customer, and unique mechanism → Pick a style preset (clinical editorial, news exposé, lifestyle magazine, warm and trustworthy) → Claude writes the full page — urgency banner to guarantee to final CTA → Nano Banana 2 generates product images and mechanism diagrams inline → Get back a complete HTML page following the same DR structure that's already scaling on Meta No copywriter back-and-forth. No designing from scratch. No starting from a blank page every time. What you get: → A production-ready HTML advertorial page you paste into Shopify → DR copy structure extracted from real pages scaling on Meta right now → AI-generated product photography and diagrams matched to your brand → 4 style presets that shift tone, colors, and authority framing per niche → A fully customizable system prompt — swap in your own templates and it follows those instead I built 3 complete advertorial pages for 3 different brands in under 5 minutes. Skincare, supplements, and pet products. All different styles, all production-ready. I put together a full playbook with the exact system prompt so you can get this running yourself. Want access for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

@spect3ral Claude

I built 10 Claude Code skills for Meta Ads They're free. Here's what they do: 👇 Operations: bleed-check: finds ad sets burning cash with zero conversions, pauses them rebalance: shifts budget from losers to winners automatically fatigue-scan: catches creative fatigue before your CPMs spike weekly-report: pulls KPIs, compares WoW, sends to Slack Creative & Intelligence: spy: scrapes competitor ads from the Ad Library, diffs weekly bulk-creative: generates 50–500 ad variations, renders to PNG hooks: writes 50+ copy variations using PAS, AIDA, BAB frameworks deploy-ads: reads a manifest, creates campaigns via API in minutes Setup & Architecture: setup-capi: generates production-ready Conversions API code audience-audit: finds overlap, maps funnel stages, fixes exclusions How to use them: Drop the .md files into .claude/commands/ Set your Meta access token Type /bleed-check, /spy, /hooks — it just runs ~25 hours/week of manual work → automated. No complex setup. No code to write. Just slash commands. Full skill files + setup guide in the article. Comment "CLAUDE" and I'll share the link (must be following!)

@veedstudio @ElevenLabs @OpenAI @n8n_io SCALE

The future of video creation is here ⚡️ Use VEED with @elevenlabs, @OpenAI, on @n8n_io Watch the full walkthrough: • Plug-and-play templates • Create 10+ videos in one click • Scale your marketing, smarter Want the template? RT + comment “SCALE” and we’ll DM it to you

@TechWith_Nova SKILL

My OpenClaw bot runs 6 AI agents 24/7 - and I'm giving away the exact skill file for free: - Scouts local businesses without a website - Audits their web presence and scores opportunities - Builds a custom demo site + walkthrough video automatically - Sends cold outreach with the live preview + payment link - Handles objections and closes the sale via email - Maintains existing clients on autopilot Bring your own API keys. No subscription. Fully automated. Reply "SKILL" and I'll send it to you (must be following)

@TapNow_AI @tapnow Free lucky

Ready to level up with Agent mode? 🤖 Show us what you've built! Share your Agent mode workflow and tag @TapNow for a chance to win. 🎁 Prize: 5,000 credits each for 50 lucky creators! #tapnow #TapTV #createinpublic

@dr_cintas NOAH

This is what practical AI agents look like. Hey Noah AI just launched an executive assistant that lives in SMS: > Zero apps or dashboards > Handles emails, scheduling, reservations.. > Learns from your behavior We're shifting from "use this app" to "just text the agent"

@Hailuo_AI hailuo free

Dropping Hailuo Light Studio Cinematic Crew in Your Pocket →Fine-tune every detail: angle, intensity & color temp →Layer your lights: mix dual sources for pro setups →20 signature presets, ready in a click Jump in with free trials! Follow @Hailuo_AI +comment +like for Free Max Plan.

@dev_manoj_shah Openclaw

My OpenClaw bot runs 6 AI agents 24/7: - Finds local businesses without a website - Builds a custom demo site for them automatically - Sends outreach with the preview + payment link - Handles objections and closes the sale Most local businesses don't have a website, this system finds them, pitches them, and collects payment automatically Reply "OpenClaw" and I'll send you early access (must be following)

Folks, if you get crypto emails from websites claiming to be associated with openclaw, it's ALWAYS a scam. We would never do that. The project is open source and non-commercial. Use the official website. Be sceptical of folks trying to build commercial wrappers on top of it.

VEED Fabric lets you scale on socials faster⚡️ Amazing talking head videos for socials With multiple emotions💥 •⁠ ⁠Expressive faces •⁠ ⁠Real emotions •⁠ ⁠Unreal speed Comment "VEED" & we'll send you FULL Guide in DMs.

@veedstudio VEED

@veedstudio VEED

Amazing AI videos now from your phone📱 With VEED's mobile app👇 • Pick any AI actor • Create AI scripts • Get auto captions & smart zoom Ship ads, product demos, and explainers in minutes. 🚨 FREE 500 Credits for every trial user RT & comment "VEED" for access in DMs

@amasad …0-2ch006w54n2lg.expo.riker.replit.dev

@amasad I built Imputation OHADA using the incredible new Agent 4! 🐘 It’s an AI accounting tool: you type a financial transaction in plain language, and it instantly generates the exact SYSCOHADA accounting entries (Debits/Credits) Watch the demo of the build below 👇 #ReplitAgent4

Software isn’t merely technical work anymore. It’s creative. Introducing Replit Agent 4. The first AI built for creative collaboration between humans and agents. Design on an infinite canvas, work with your team, run parallel agents, and ship working apps, sites, slides & more.

@get_artcraft Seedance 2

🚨Free Seedance 2.0 Film Set Giveaway!🚨 Open Source Virtual Film Set with Seedance 2.0 Giving 10 monthly subs. How to win ⚡️ Like, repost, and comment "seedance" ⏰ 10 lucky winners will be announced in the next 24 hours Must be following @get_artcraft ! Your Film Studio

Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 changes that improved the validation loss. I tested these changes yesterday and all of them were additive and transferred to larger (depth=24) models. Stacking up all of these changes, today I measured that the leaderboard's "Time to GPT-2" drops from 2.02 hours to 1.80 hours (~11% improvement), this will be the new leaderboard entry. So yes, these are real improvements and they make an actual difference. I am mildly surprised that my very first naive attempt already worked this well on top of what I thought was already a fairly manually well-tuned project. This is a first for me because I am very used to doing the iterative optimization of neural network training manually. You come up with ideas, you implement them, you check if they work (better validation loss), you come up with new ideas based on that, you read some papers for inspiration, etc etc. This is the bread and butter of what I do daily for 2 decades. Seeing the agent do this entire workflow end-to-end and all by itself as it worked through approx. 700 changes autonomously is wild. It really looked at the sequence of results of experiments and used that to plan the next ones. It's not novel, ground-breaking "research" (yet), but all the adjustments are "real", I didn't find them manually previously, and they stack up and actually improved nanochat. Among the bigger things e.g.: - It noticed an oversight that my parameterless QKnorm didn't have a scaler multiplier attached, so my attention was too diffuse. The agent found multipliers to sharpen it, pointing to future work. - It found that the Value Embeddings really like regularization and I wasn't applying any (oops). - It found that my banded attention was too conservative (i forgot to tune it). - It found that AdamW betas were all messed up. - It tuned the weight decay schedule. - It tuned the network initialization. This is on top of all the tuning I've already done over a good amount of time. The exact commit is here, from this "round 1" of autoresearch. I am going to kick off "round 2", and in parallel I am looking at how multiple agents can collaborate to unlock parallelism. github.com/karpathy/nanoc… All LLM frontier labs will do this. It's the final boss battle. It's a lot more complex at scale of course - you don't just have a single train. py file to tune. But doing it is "just engineering" and it's going to work. You spin up a swarm of agents, you have them collaborate to tune smaller models, you promote the most promising ideas to increasingly larger scales, and humans (optionally) contribute on the edges. And more generally, *any* metric you care about that is reasonably efficient to evaluate (or that has more efficient proxy metrics such as training a smaller network) can be autoresearched by an agent swarm. It's worth thinking about whether your problem falls into this bucket too.