Ben Keogh 🏴

One prompt. Four design systems. Four completely different sign-up modals. The AI didn't guess any of this. Layout gave it the design system. Same prompt. Your brand. layout.design

If you made $500,000 per day, every single day since the Great Pyramids were built, you would have less than half of what the US govt has borrowed since June.

About to hit 100 users on @layout_design. Hundreds more on the waitlist. Design teams from Fortune 500s, major fintechs, global e-commerce brands, streaming platforms, even national government services. All hitting the same wall: AI generates UI fast but doesn't know your design system. That's the problem we're solving. First 100 are the hardest. The fact that these teams found us organically tells me we're onto something. Request early access at layout.design

@mikefutia BANANA

Claude Code + Nano Banana 2 is f*cking cracked 🤯 I built a skill inside Claude Code that writes JSON image prompts for Nano Banana 2, and the outputs look like they came from a professional photo shoot. One plain-text prompt. Claude rewrites it as structured JSON with lighting, camera, composition, style, and negative prompts. Then fires it off to Nano Banana 2. All inside Claude Code. Perfect for DTC brands and agencies who need high-volume ad creative without booking a shoot. If you're using Nano Banana 2 for product shots and lifestyle images but every generation feels like pulling a slot machine lever — random lighting, inconsistent style, plastic skin, misspelled labels ... This skill fixes the entire output: → You describe what you want in plain English → Claude rewrites it as a structured JSON prompt (lighting, camera angle, lens, depth of field, color grading — all of it) → Fires it to Nano Banana 2 via API → Saves the prompt + image in organized folders → You iterate on the style until it's dialed, then every output matches No more slot machine prompting. No more inconsistent brand imagery. No more burning credits on unusable generations. What you get: - Photo-realistic product shots and lifestyle images on demand - Full control over style, lighting, composition, and camera settings - Saved JSON prompts you can reuse across every campaign - A skill that gets smarter the more feedback you give it Built 100% in Claude Code with a custom skill + Python scripts. I put together a full playbook showing the exact skill, the JSON schema, and the workflow to set this up yourself. Want the full playbook? > Like this post > Comment "BANANA" And I'll send it over (must be following so I can DM)

My new favorite insult is calling someone’s job a Claude skill.

@BiggestComeback @dpolehn And mine

@dpolehn That is exactly what happened to mine this past December.

I didn't think this was how my Garmin would break. Any good watch recommendations?

@paolo_scales GUIDE

I booked over 147 calls in the last 30 days ONLY thanks to LinkedIn You can literally steal my whole inbound + outbound system for yourself Will not be gatekeeping anything... RT + reply "GUIDE" and I'll send it to you

Creme is live. Browser-based live coding for music. Zero installation. Sub-150ms latency. What you get: Simple pattern language for beats and melodies. 54+ effects for sound design. AI assistance to generate code from descriptions. Polyrhythmic support for complex grooves. Works on any device with a modern browser. This one's for the bedroom producers and code-curious musicians. creme.music

@pierreeliottlal CLAUDE

Claude Cowork just KILLED manual outreach. I used to grind for hours on LinkedIn. Now? My AI stack does it better. - No "Hey {{first_name}}" spam - Natural, multi-step conversations - 12+ hours saved this week The result: 500+ conversations with human-level reply rates. I packaged the entire system (prompts + workflow) into a FREE doc. Want it? Repost (so others see it) Comment "CLAUDE" & I'll DM you.

The problem with every Airdrop alternative I've tried: Snapdrop: Need browser open on both devices Bluetooth: Painfully slow, constant pairing issues Cloud sync: Upload, wait, download, wait USB: MTP is a disaster on Mac What I want: 1. QuickShare from Android 2. Mac appears in the list 3. Tap 4. File arrives That's it. That's the entire feature spec for Flyng.

@aakashgupta If you like Ralph, you should check out PreClaude: preclaude.com - 27 slash commands, 16 specialist agents, and Ralph autonomous builder — all pre-configured and ready to use.

Ralph may be the most important thing to learn in AI right now. Someone used this technique to deliver an entire contract that would have cost $50,000 to outsource. Total API costs: $297. At a Y Combinator hackathon, teams shipped 6 working repositories overnight using the same approach. Geoffrey Huntley, who invented this, built an entire programming language over 3 months while barely touching his keyboard. Ralph is a bash loop that runs an AI coding agent repeatedly until a task is done. That’s it. While you sleep, while you eat dinner, while you do anything else, the loop keeps going. It picks up a task, builds it, checks if it works, saves the progress, picks the next task. When you wake up, features are finished. Why this works when normal AI coding fails: most people open Cursor or Claude with a vague idea and no structure. 45 minutes later they’re fixing the same bug for the third time. The AI forgot what they were building. The context got polluted. They’re frustrated and nothing shipped. The problem is task size. One feature has 20 pieces. The AI tries to hold all of them at once. It can’t. It hallucinates. It contradicts itself. You end up babysitting. Ralph fixes this by breaking work into pieces small enough that the AI finishes each one before it forgets what it’s doing. Each loop iteration starts fresh. Clean context. No accumulated confusion. Memory persists through git commits, a progress file, and a task list. The AI reads what happened last time, learns from mistakes, picks the next task. The workflow: Step 1: Describe what you want in plain language. Talk for 2-3 minutes. “I want users to filter tasks by priority. High, medium, low. A dropdown with all three options plus ‘all’. Selecting one filters the list immediately.” Then tell the AI to convert your rambling into a formal requirements list. Step 2: Break requirements into atomic tasks with binary success criteria. Good: “Add a priority column that defaults to medium.” Bad: “Make it work well.” The AI needs to know when it’s done without asking you. Pass or fail. Yes or no. Step 3: Run the loop. Ralph grabs a task, builds it, runs tests, commits if it passes, moves to the next one. You set a limit (10 rounds, 14 rounds, 20 rounds). It runs until everything passes or hits your limit. The math is brutal. A typical Ralph run: 10 iterations, roughly $30 in API costs. A senior developer costs $400-600 per day fully loaded. If Ralph gets you 90% there and you spend an hour on cleanup, you just converted an 8-hour workday into 1 hour plus $30. That’s $500+ of labor arbitrage per feature. Compound that across a month of building. Ralph can replace the majority of outsourcing for greenfield projects. The technique is “deterministically bad in an undeterministic world,” meaning when it fails, it fails predictably. You tune it like a guitar. When Ralph screws up a specific way, you add a guardrail to the prompt. The failures become instructions. The real shift is in role. You stop being the person who writes code. You become the person who writes requirements, defines acceptance criteria, and reviews output. Product designer, not engineer. “Software development as a profession is effectively dead. Software engineering is more alive than ever.” The people who understand systems, architecture, requirements, and quality will thrive. The people whose value was typing code faster are already obsolete. The gap forming right now: builders who know Ralph are shipping 5-10x more than everyone around them. Nobody understands how. The technique is free and open source. The barrier is just knowing it exists and spending 30 minutes to understand the pattern. Three months from now this will be in every YouTube tutorial and paid course. The window is right now, while most developers are still prompting Claude one function at a time and wondering why AI “doesn’t work for them.” github.com/snark-tank/ral…

@damianplayer If you like Ralph, you should check out PreClaude: preclaude.com - 27 slash commands, 16 specialist agents, and Ralph autonomous builder — all pre-configured and ready to use.

@superduperui has 17 app clones now. The pattern I see: successful apps don't have every feature. They have the right features, done well. Notion didn't launch with databases. Stripe didn't launch with subscriptions. Core use case first. Everything else is iteration.

@coldemailchris Cold

This masterclass document covers everything I know about cold email copywriting after sending 5,000,000+ emails over the last 3 years. In it contains 175 minutes of content across unique 9 trainings: > Fundamentals of Excellent Cold Email Copywriting > Understanding The Psychology of Cold Email > Our Top Cold Email Script Frameworks > Cold Email Script Writing Checklist > Understanding Personalized Relevance (Messaging Concept Training) > How to Clear Email Scripts from Spam Words > How to Write Cold Email Script Messaging with AI > How to Write Follow-up Emails with AI > Live AI Cold Email Script Writing Walkthrough Want access to the doc? 👉 Like + Comment “Cold” and I’ll DM you the document link. (Must be following to receive DM)

@superduperui now has 17 UI clones. Latest addition: Perplexity (271 screens) Every search interaction. Every state. Every component. Study how the best apps are built: superduperui.com

I just joined the Overheard waitlist! Join me and skip the line: waitstack.co/join/overheard…

Meet Nattr.ai — one chat, six AIs. Claude, GPT-4, Gemini, Grok, DeepSeek and Qwen all answering your question at the same time. Type @all and get multiple perspectives instantly — no tabs, no copy-paste, no switching tools. Perfect for coding, research, planning, or when you want fast cross-validation from different models. Try it here: nattr.ai

Amazing documentary. The segment about Theme Park on the Amiga delivered a shot of warm fuzzy nostalgia.

Thrilled to celebrate 5 years of AlphaFold 2! It’s now been used by over 3 million researchers around the world to accelerate their vital research - and it was an honour of a lifetime for our work to be recognised last year with the Nobel Prize! Proof of AI’s potential to enable science at digital speed 🚀 To honour the anniversary, we’ve made The Thinking Game film available for free on our YouTube channel - it’s a great look behind the scenes of AlphaFold & our journey to AGI.