Andrew and Ulad are cracked. I've been watching them ship over the last 6 months. coddev is by far the highest quality vibe-coding tool out there.

- I'm being ambitious so it'll likely take me 2 weeks to get this working

Day 4 & 5: - Got a few of the open source manus projects running - They work but the use of the browser isn't super consistent. I think I'll build my own execution engine while taking inspiration from these projects - Have to build a voice agent to plug into the engine

Day 3: - Heads down coding Wish I had more to share but don't for now

I'm curious. What do you do?

Day 2: - Found a cheap freelancer to help with content - Heads down coding yesterday, today, and tomorrow I'm intentionally not sharing what I'm building because it's embarrassingly bad. I'll share it once it actually delivers the intended value prop

Btw, I'm an optimistic person but I give myself a < 1% chance of hitting that goal. Forget $50k, getting to $500 mrr is hard But that's not the point. The point is I'm locked in regardless of the result

Uh, when I asked for public accountability I didn't mean this much 😂 I would've put some real thought into that MRR number if I knew 800k people would see this and if I knew I wouldn't be tweeting to myself

My goals for this week: - Update the app so it delivers recurring value - Figure out how to convert better from TikTok to app downloads - Automate posting, it's eating up valuable time I expect to be able to set a public revenue goal by this time next week.

3. TikTok as my main distribution lever is a little fickle - I learned a little too late that accounts get shadow banned quickly so you need multiple accounts - Once you've had a few videos go viral, that format gets saturated quickly - Posting is a slog. It takes 1.5 hours a day

1. Content from TikTok hasn't converted well into app downloads. 600k views has converted into ~1k downloads. 2. The app doesn't deliver recurring value so people aren't incentivized to continue past the free trial (only a handful of people have continued their subscription)

Day 1: I cheated a little bit. I actually started last week. The first 3 weeks are an exploration period. Last week, I started a TikTok to test demand for an idea. I grew it to 4k followers and 500k views and shipped an app. But the app has so far failed. Here's why:

Why $50k MRR and why 80 days? 2 stupid reasons: 1. 80 days because the PMF or die guys did 90 days so I'm challenging myself to 10 fewer days 2. $50k MRR because that's about how much a mid-level engineer at OpenAI makes. Why OpenAI? Setting the bar high

I'm starting something new today I'm starting from scratch and giving myself 80 days to get to $50k MRR, otherwise I'll go back to a "normal" job. I'll be posting everyday for public accountability. My tweets average a staggering 60 views but that's enough

Seems like OpenAI made a change. The content policy isn't as strict anymore

My only problem with OpenAI’s new image gen model is it’s too woke. Half of my very innocent requests are blocked by their content policy

OpenAI image generation > Gemini 2.0 flash exp

Gemini has the worst documentation known to man kind. @GoogleAI PSA use the google/genai package not the google/generative-ai package for all new models

I can't be the only person that always switches to Edit mode with Claude 3.5 in Cursor for every request. Ask and Agent goes way overboard

Is there a modern version of https://t.co/8Zrm3XECEz that people use for icons these days? Or a gen AI alternative to it? Looking to create a few icons with a specific style that I want for an app