bawse

Built a one-command OpenClaw on AWS launcher. No need for a Mac Mini. Deploying Openclaw on AWS just got so much easier. And I’ve open-sourced it! Github link in the comments 👇

@neda_sefati any cafe near One Central will do the job

Any good cafes around here?

@jesse_vermeulen this is an oscar-deserving performance

day in the life of a performative founder

Have you read this book?

@rezoundous i think it's beyond even senior at this point

It's crazy that AI SWE capabilities went from entry to senior in a year.

Did you read the code today?

@sflorimm .app also slaps

best one? .ai .com

@DavidOndrej1 there should be a token olympics see who can achieve a given goal in the least amount of tokens possible

OpenRouter should turn into a bank. Soon enough we will be taking out Token-loans

@DavidOndrej1 its gonna be amazing for 2 weeks, then it's the same playbook all over again > quality degradation > issues with limits > codex swoops in

Anthropic is about to release a new model

@thekitze ngl, seeing "smoking gun" feels so good when you've been trying to debug for hours

top 4 gpt 5 phrases - smoking gun - i ran the smoke tests - not gonna hand wave it - goblin

@afscott distribute 1 SOL for each tooth you pull out

my dentist offered me his clinic as a video set for solana content - ideas ?

@afscott what's one good idea that really made you think?

i know an event was a good one based on the number of new ideas that i get

@dara_venture You're right that it's frozen in the hospitality and related industries, but people are quietly deploying capital in other sectors. May not be Family offices specifically though.

Hearing from multiple UAE Family Offices, that capital deployment is essentially frozen. Most have deep exposure to hospitality and they're bleeding. Protecting core assets, drawing from other pockets to plug the gap. Don't expect a shift until there's a firm peace agreement on the table.

the honest take on vibe coding after months of shipping with it daily you save massive time on the first 80%. scaffolding, boilerplate, integrations, CRUD. stuff that used to take days takes hours but the last 20% still takes the same amount of time. debugging edge cases, verifying data integrity, making sure the LLM didn't hallucinate a dependency that doesn't exist net result: i ship 3-4x more projects but each one still needs a real engineer reviewing everything before it goes live vibe coding is a legitimate product strategy. it is not a replacement for knowing what you're doing

@jamesqquick absolutely makes sense, but struggled with it a lot earlier on in my career

Developers. Is “egress” a word you immediately resonate with? Is it something that has tangible meaning to you without further discussion?

@zeroxjackson write your infra as code and you never have to look at a dashboard ever again

There is no technical reason for infrastructure to be more complicated than the Supabase dashboard.

@mikefutia STATICS

I just vibe coded a static ad generator in Claude Code that creates 100+ Facebook ads in minutes 🤯 All using the new insane ChatGPT Images 2.0 model. Upload one image of your brand or product → get 100+ brand-new ad concepts across every DR archetype, each one matched to a specific customer persona. Built 100% in Claude Code. Perfect for DTC brands and agencies who need to rapidly test mass creative statics at scale. Here's how it works: → Upload a single image of your brand or product → Add your brand kit (colors, fonts, logos) → Tool generates 10 customer personas from your brand research (Depleted Woman, Burned-Out Professional, Brain-Fogged Mom) → Pick how many concepts you want (40, 60, 100+) across archetypes — Bold Billboard, Listicle, iPhone Notes, iMessage, UI Hijack, Us vs Them, Press/Authority, Lo-Fi Sketch, UGC → Hit "Generate All" → finished ads render in seconds, each one targeting a specific persona with its own copy angle No more paying "static ad agencies" $3,000 per month. What you get: - 100+ on-brand static ads from a single product photo - Perfect product and text adherence powered by ChatGPT Images 2.0 - Persona-specific copy on every ad, no generic hooks - Iterate and scale statics in minutes instead of weeks - Reusable brand kits + persona libraries you build once and pull from forever - Every ad ships with the exact prompt and persona attached, so you can iterate instead of starting over. This is essentially a static ad agency in a box. I put together a complete playbook which includes EVERY single prompt I used to make this in Claude Code. Want all the prompts for free? > Like this post > Comment "STATICS" And I'll send it over (must be following so I can DM)

@notgodwin2 @iirfan fyi I like both tools and use them side-by-side daily. I'm not married to a tool, and you shouldn't be either

@bawsebuilds @iirfan Codex people are just hating for the love of the game. Deep down they know Claude is better. Gotta keep the engagement up

Codex can never

@OxNalds last name ever, first name greatest

Let’s have it…

@jamesqquick The easiest integration right now for this particular workflow is Cursor Cloud Agents. You can connect your github via the Cursor dashboard and wire it up easily.

Whats your current setup for running code focused cloud agents? Specifically, a setup to take tickets/issues and create a pr. All in the cloud.