prompt diff: 🟩⬛️⬛️⬛️⬛️⬛️
Vanlifing
Joined July 2025
- Tweets1.6K
- Following426
- Followers79
- Likes2.7K
Cody Bontecou retweeted
I'm going to show this to every founder who refuses to launch early.
teapaw.org/broadglow/status/20670…
Cody Bontecou retweeted
Currently working on giving users access to their data via .md files.
apps.apple.com/us/app/health…
apps.apple.com/us/app/iso-me…
apps.apple.com/us/app/sync-m…
Cody Bontecou retweeted
Haha! Fair. It's all moving so fast.
@mitsuhiko article lucumr.pocoo.org/2026/1/31/p… convinced me to use it and tbh, it's incredible.
The philosophical idea of "using software that builds more software" makes a lot of sense with agents.
Cody Bontecou retweeted
Billing different based on text contained in the system prompt is a really bad look
Cody Bontecou retweeted
You have no experience.
You’ve never started a company.
You’ve never had a full time job.
Nike is going to kill you.
You’re a kid.
You don’t have technical skills.
You shouldn’t build hardware.
Apple is going to kill you.
You can’t build hardware.
You can’t measure heart rate non-invasively.
Athletes don’t care about recovery.
Under Armour is going to kill you.
It won’t be accurate.
You don’t listen.
You’re an ineffective leader.
You can’t recruit great talent.
You’re going to have to pay every athlete.
You can’t measure sleep non-invasively.
It’s too expensive to research.
Athletes are a small market.
The product costs too much to make.
The product costs too much to sell.
Your valuation is too high.
Consumers aren’t going to want it.
Hardware is too hard.
You should measure steps.
Fitbit is going to kill you.
You can’t build a marketing engine.
You can’t raise enough money.
You need a real CEO.
Google is going to kill you.
You can’t be a subscription.
You can’t build a brand.
You can’t do consumer in Boston.
Your valuation is too high.
You shouldn’t make accessories.
You shouldn’t make apparel.
Lululemon is going to kill you.
You can’t predict Covid.
Stay in your niche.
You are going to run out of money.
You can’t build a health platform.
Amazon is going to kill you.
You can’t measure blood pressure.
You can’t get medical approvals.
The market is too small.
You don’t understand AI.
The market is too competitive.
It won’t work internationally.
The supply chain is too complicated.
You can’t build an AI.
You can’t raise enough money.
It’s too competitive.
Healthcare isn’t going to want it.
…
Just keep going ✌️
Cody Bontecou retweeted
Use pi as your agent harness and move between the two via /model.
Turns out the model beneath isn't all that important - it's the tools and system prompt that carry most of the weight.
Cody Bontecou retweeted
Generative AI CAN be art.
Keyword "can".
Banging on the piano creates SOUND. But that's not ART.
Clicking "generate" on @soraofficialapp creates a VIDEO. But that's not ART.
So what is art?
Directing AI with intention.
Defining a vision for what story and/or emotion you want to convey, and then prompting AI with hyperspecific instructions to bring said vision to life.
I created this transition video using Kling 2.1 and @higgsfield_ai.
But I also had to:
- intentionally choose which of my own shots to create transitions for
- refine and iterate my prompt for each transition
- choose music that captures the right emotion
- speed ramp the videos to match the music
- add LAYERS of sound effects: ambiance, whooshes, risers, accents
AI is the highest leverage creative tool in human history.
Master this tool, develop your taste, and you'll dominate content in 2026.
Cody Bontecou retweeted
I quite my job over a year ago with ~$50,000 USD saved up thinking it would last a year. I thought all I needed to be successful was committing myself entirely to my ideas and eventually I'd become financially free.
Well... about 10 months in I had made $15 from my projects and my bank account was at ~$10,000.
Money anxiety took over and I began looking for work.
Quickly I actually found part-time work via Hackernews' monthly Who's Hiring threads. I've bounced around to a few clients now, each paying me slightly more than the last, and it's worked out very well.
I now work 20-30hrs per week and have tons of time and energy to work on my side projects as well.
All while seeing my bank account grow.
Cody Bontecou retweeted
"It is pretty amazing how much progress you can make if you just have people from different disciplines sit together."
Mark discusses the overlooked value of having employees across different disciplines simply sit together.
@czi @officialbiohub
Priscilla Chan and Mark Zuckerberg co-founded the Chan Zuckerberg Initiative (CZI) in 2015, committing 99% of their Meta shares to advance science, education, and opportunity. As a pediatrician and CEO of Meta respectively, they've built CZI into one of the most ambitious technology-driven philanthropic organizations with a moonshot goal to help cure, prevent, or manage all diseases by the end of the century.
In this episode, we sit down with Priscilla and Mark to unpack how CZI bridges state-of-the-art AI with open biomedical research, their investments in open-source tools like the Human Cell Atlas, their philosophy on building teams across different disciplines, and what they envision the future of healthcare.
@czi @swyx @FanaHOVA
Cody Bontecou retweeted
100%.
I tried this, quitting my job with $50k in the bank.
After 9 months, it was $10k and I had generated $15 from side projects.
Turns out it wasn’t my job stopping me from making money from my side projects…
Cody Bontecou retweeted
I’ll happily pay $200/month for a marketing solution that provides the same level of value as Claude Code.
Cody Bontecou retweeted
Day 1 of sharing my app:
My husband and I created a feedback button that creates GitHub issues and generates pull requests.
A better way to gather user feedback 🤓
You can find it here: pullreque.st
