JJ Vlad

[𝐍𝐨𝐚𝐡 @noahelhadedy]

9 websites I use for web design inspiration

1. https://t.co/TjOqlpOC16
2. https://t.co/WOWlwlMZ2w
3. https://t.co/sjGdqLhHpc
4. https://t.co/PRdhMuEBNW
5. https://t.co/R3wHSBbol9
6. https://t.co/WyVAx0IMYr
7. https://t.co/wUKT8Ps19o
8. https://t.co/PDFNn32lLP
9. https://t.co/GXeovza5gs

What did I miss?

[Tom Dörr @tom_doerr]

Downloads videos, courses, and music from 1,800+ sites including Udemy and YouTube, then transcribes and converts them.

https://t.co/pqVhTNEmfd

[tobarra @txbrraa]

Este tipo explica cómo crear páginas web profesionales con GPT-5.6 Sol.

Un tutorial de 21 minutos donde explica paso a paso cómo construir diseños con un acabado cinematográfico.

🔖 Guárdalo. Vale cada minuto.

[Hakimi Eiqbal @hakimieiqbal]

want to see how far you can get with AI?

here's 1000 free credits to start:

WLCM0730

QuadcodeAI gives you coding, image, video and reasoning models in one workspace

https://t.co/LG13qxlcrZ

[Ram Singh Verma @RamSingh_369]

BREAKING NEWS!

The engineer who built Claude Code from scratch just released a 28-minute video that's pure gold: how to write prompts that deliver ridiculously good results.

I've seen $300 courses that don't even come close to what he explains in the first 10 minutes.

CLAUDE.md files, memory shortcuts, parallel sessions, and prompting patterns that almost no one uses...

All in one single video. Completely free. No fluff.

Whether you're a developer, just starting, or have already been using Claude for months, this changes the game for you starting today.

Save. Watch. Share.

[Nainsi Dwivedi @NainsiDwiv50980]

This 2-hour Stanford lecture will teach you how to build AI agents, write prompts, and implement RAG — better than every Claude and AI tutorial you've watched this year combined.

This is exactly how Stanford trains its own engineers.

Free. On YouTube.

Bookmark this before you forget. 👇

[Khairallah AL-Awady @eng_khairallah1]

🚨 INSTEAD OF WATCHING NETFLIX TONIGHT.

Spend 5 hours with this.

Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything.

The people who watch this tonight will wake up tomorrow with a new skill.

Watch it and Bookmark it now.

[Om Patel @om_patel5]

SOMEONE BUILT A SINGLE CLAUDE.MD FILE THAT FIXES EVERY BAD HABIT CLAUDE CODE HAS AND IT HIT 78.5K STARS

it's based on andrej karpathy's public observations about how LLMs write code

the problem he pointed out is that claude makes silent assumptions, overcomplicates everything, writes 1000 lines when 100 would do, and sometimes deletes code it doesn't fully understand as a side effect

so forrestchang turned karpathy's critique into 4 behavioral principles and dropped them in one claude.md file:

1\ surface your assumptions

don't pick an interpretation silently. if there are multiple ways to read the task, say so. if uncertain, ask. push back when something doesn't make sense instead of just running with a bad plan

2\ minimum viable code

no speculative features, no abstractions for single use code, no "flexibility" you weren't asked for.

if you wrote 200 lines and 50 would work, REWRITE IT. ask yourself if a senior engineer would call this overcomplicated

3\ surgical changes only

don't touch code you don't fully understand, don't refactor unrelated stuff as a side effect, don't delete comments because they look unnecessary. only change what the task actually requires

4\ goal driven execution

give claude success criteria instead of step by step instructions.

karpathy's exact quote: "LLMs are exceptionally good at looping until they meet specific goals. don't tell it what to do, give it success criteria and watch it go"

one file has 78.5k STARS AND 7.4k FORKS on a single github repo.

install is one curl command that drops it straight into your ~/.claude folder

[How To Prompt @HowToPrompt__]

Someone just open-sourced a full 3D Gaussian Splat editor that runs 100% in your browser.

It's called SuperSplat. You can inspect, edit, optimize, and publish photorealistic 3D scenes with zero install.

100% Open Source.

[Mike Futia @mikefutia]

I just vibe coded a static ad generator in Claude Code that creates 100+ Meta ads in minutes.

All using the new, insane ChatGPT Images 2.0 model.

One competitor ad + your product photo + your brand kit = dozens of on-brand variations, each targeting a different customer persona.

Built 100% in Claude Code on the new ChatGPT Images 2.0.

Perfect for DTC brands and agencies who need more statics at scale.

Here's how it works:

→ Upload any competitor ad as your reference template
→ Add your product photos and brand kit (colors, fonts, logos)
→ AI generates 10 customer profiles from your brand research
→ Pick how many variations you want (10, 20, 30)
→ Tool fires every prompt to ChatGPT Images 2.0 with persona-specific copy for each one

No designer back-and-forth. No Canva templates. No generic "Shop Now" on everything.

What you get:

→ Ads that mirror winning concepts in your brand's voice
→ Text that actually renders correctly (the new model handles dense copy, logos, and multi-language callouts cleanly)
→ Copy targeted to specific customer pain points and personas
→ Multi-brand/client support with saved brand kits
→ Reusable customer profiles you build once and generate from forever

I recorded a full walkthrough showing exactly how this works, including ALL the prompts I used so you can build it yourself.

Want access to all the prompts for free?

> Like this post
> Comment "STATICS"

And I'll send it over (must be following so I can DM)

[Chris Laub @ChrisLaubAI]

A Rust dev just killed Headless Chrome.

It's called Obscura. The open-source headless browser purpose-built for AI agents and scrapers at scale.

Chrome vs Obscura:

- Memory: 200MB+ → 30MB
- Binary: 300MB+ → 70MB
- Page load: 500ms → 85ms
- Startup: 2s → Instant
- Anti-detect: None → Built-in

Single binary. No Node, no Chrome, no dependencies.

Stealth mode is brutal:

→ Per-session fingerprint randomization (GPU, canvas, audio, battery)
→ 3,520 tracker domains blocked by default
→ navigator.webdriver masked to match real Chrome
→ Native function masking so detectors can't sniff it out

Drop-in replacement for Puppeteer and Playwright over CDP. Zero code changes.

If you run agents or serious scraping at scale, this repo prints money.

100% Opensource.

[LakeSail @LakeSail]

Spark rebuilt in Rust — no JVM, 8x faster, 94% less cost.

[Tran Mau Tri Tam ✪ @tranmautritam]

Paste a URL. Get a DESIGN. md

[Tw93 @HiTw93]

I recently discovered a super cool website inspection tool called Web-Check. It has a strong hacker vibe.

It lets you inspect almost everything about a website: IP details, SSL, DNS records, cookies, domain info, crawler rules, server location, redirect history, open ports, traceroute, DNSSEC, site performance, associated hostnames, and more.
https://t.co/A5B83COLK7

[Mike Futia @mikefutia]

Nano Banana Pro is the GOTA for static ads 🍌

But it only generates one image at a time.

This n8n agent generates 1,000+ ad variations from a single product photo, fully automated.

Perfect for e-comm brands & agencies who need volume without the manual grind.

Here's the problem:

You're testing static ads at scale.

You need 50, 100, maybe 500 variations to find winners.

But you're sitting there prompting Nano Banana one image at a time, downloading, organizing, repeating.

That's not a creative workflow. That's a part-time job.

This n8n agent fixes it:

→ Upload one product image via n8n form
→ OpenAI Vision analyzes your product automatically
→ AI generates custom image prompts (you choose how many)
→ Nano Banana creates every variation on demand
→ All images auto-stored in Box. com for instant access

No manual prompting.

No one-by-one downloads.

No folder chaos.

What you get:

- 50, 100, or 1,000 ad variations from one upload
- AI-generated prompts tailored to your product
- Every image organized and ready to test
- Hours of work compressed into minutes

Built 100% in n8n.

Want the full workflow?

> Comment "NANO" +
> Like this post

And I'll send it over (must be following so I can DM)

[J.B. @VibeMarketer_]

This AI builds complete fashion campaigns from a single product photo in under 10 minutes.

most fashion brands spend $10K+ on photoshoots and wait weeks to get enough assets to test new markets or refresh their creative

this agent eliminates that completely. here's how you can use it:

you upload your product packshot → AI generates the fashion model (age, style, pose — all on-brand) → model is placed in studio-quality environments → your product is integrated onto the model with perfect consistency → AI creates 10+ variations (different poses, angles, settings) → turn static shots into video with one click

it's the equivalent of doing:

- a full fashion photoshoot
- a model casting process
- multiple location setups
- video production
- localization adaptations

all in minutes.

this is perfect for brands that need to:

- launch campaigns with zero photoshoot budget
- extend the life of existing product shots
- test new markets without reshooting
- refresh creative weekly without production delays

i'm giving away the full agent template + setup walkthrough so you can build this yourself.

comment "FASHION" below + like this post and I'll send it over.

(must be following so i can dm you)

[Edward Frank Morris 🦇 @ThatsEFM]

This shouldn’t exist.

Nano Banana Pro + @Gammaapp recreated an Apple iPhone launch in under a minute. By myself.

No million dollar team.

Hyper realistic. Built in a browser.

Comment “Gamma” and I’ll send you 500 prompts.

🧵

[Paul Sims @SimslearnAi]

Nano Banana + MakeUGC + Veo3 = AI content Factory

This agent pumps out hundreds of ads daily — fully automated.

- No $300 creators
- No $10K/month agency fees
- No products

Comment “HK” and I'll send it for FREE!
(must be following)

[Mike Futia @mikefutia]

I just swapped a UGC creator with an AI character in under 10 minutes 🤯

Same video. Same expressions. Same lip sync.

Completely different face.

This workflow is perfect for DTC brands & agencies who want to test multiple creator variations without filming anyone new.

Here's the use case:

You've got a UGC video that's printing money.

The script converts. The pacing is dialed. The energy is right.

But you want to test different faces—different ages, demographics, vibes—to see what actually drives the highest CTR.

The old way:

→ Hire 5 new creators
→ Brief each one
→ Pray they match the original energy
→ Pay $500+ per video
→ Wait 2-3 weeks

The AI way:

→ Take your original UGC video
→ Generate an AI character with Nano Banana
→ Run both through FAL AI's Wan Animate
→ AI swaps the face while keeping every expression & movement
→ Done in minutes

The motion tracking is ridiculous.

Every smile. Every head tilt. Every hand movement.

Perfectly mapped onto the new face.

What this unlocks:

→ One winning script, 5 different creator looks
→ A/B test demographics without reshooting
→ Localize ads for different markets instantly
→ Refresh fatigued creative with a new face

I recorded a full step-by-step Loom showing exactly how to do this.

Want the tutorial?

-> Comment "FACE"
-> Like this post

And I'll send it over (must be following so I can DM)

(Please use responsibly 😂)