Quick share, because none of this would have happened without Nate's videos and the stuff I've picked up here. Quick context — I run a small luxury travel company in Portugal. Started using Claude Code as my assistant a few months ago after going down the rabbit hole on Nate's content. At some point I thought, ok, let me really test this thing. Build a brand from scratch, no agency, no developer, no designer. Just me and Claude. That brand is Latent States. Premium streetwear with words that describe what an AI does when it's "thinking" — mulling, noodling, processing, buffering, simmering. Print-on-demand so no inventory risk. Here's what we built together: - Brand, logo, copy, the whole identity - Shopify store, customised through the API (theme, sections, collections) - 60 products created on Printify programmatically - Instagram, Facebook and TikTok publishers via their APIs - Python scripts to generate all the social visuals and print files - An n8n workflow that auto-posts 3x a day from a content queue - Custom domain email through Cloudflare and Resend, basically free Site is live, posts are going out on their own, store is taking orders. The crazy part is I never wrote a line of this stuff before — Claude did the heavy lifting, I made the decisions. What I'm stuck on now is traffic. The technical side is done, but getting people to actually land on the site is a different game. So if anyone has a minute: latentst.com @latentstates on Instagram and TikTok Tell me what you think. What would you do in my place to get the first real wave of visitors and buyers? Paid, organic, partnerships, anything — I'm all ears.

OpenAI just dropped GPT 5.5 and the benchmarks look strong against Opus 4.7, but benchmarks only tell part of the story. I ran four head-to-head experiments in Codex and Claude Code to see how the models actually compare on speed, cost, and output quality. The results were not what I expected.

I'm trying to create reports using Claude Code and it says Prompt is too long. Anyone got how can we fix this?

OpenAI just dropped GPT Image 2, and it's now ranked the #1 image model, beating Nano Banana 2 by 242 points on arena.ai. I ran 30 side-by-side matchups between the two models, had Claude Opus 4.7 judge them, and then pushed GPT Image 2 through 15+ real use cases like product packaging, ad creatives, real estate staging, logo variants, and book covers. If you use AI images for content or work, this comparison will show you which model to reach for. GITHUB REPO

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊