THE 64 MINUTE OPENAI CODEX MASTERCLASS IS HERE
if you've been meaning to learn Codex, this is the episode for you, we cover:
1/ Claude vs Codex (what's better?)
2/How to run Claude Code inside Codex (really cool)
3/Why GPT 5.5 changed everything for browser agents 4/How to create skills (reusable agents you build once and call by name forever)
5/How to connect Notion with surgical permissions (one database, not the whole workspace)
6/How to use Remotion inside Codex to create videos
7/ How to one-shot full mobile apps in Swift
8/The 4 projects to run on day one to get up to speed fast
shoutout to @rileybrown for coming onto @startupideaspod for the 5th time. every episode he delivers. this one is the Codex masterclass.
if you've been meaning to learn Codex, this is the episode.
100% free
i just want to see you build your ideas.
https://t.co/JELPC7WQhs
watch
My data sets had held it for years as ‘new money’...like from 1999 onward. This set actualized as ‘BITCOIN’ and ‘CRYPTOS’.
It was 2011 or 2012, when there was confirmation that BTC was the first of the ‘new money’ set to appear. There was a subset that grew into a point of near separation with its own internal structure.
This subset is very difficult to label effectively as it is very dynamic. This subset described a point where we would have the ‘new money’ morph into a ‘dynamic money (self altering)’.
This subset was seemingly fulfilled by the ‘smart-contracts’ of the evolving Blockchain ecosystem.
Seemingly...even now that subset core elements still can be located. They continue to grow and evolve in surprising directions.
Examining this data has some clear pointers to this Summer in which we will have our vision of BTC ‘diverted’ by its bouncing around 77K for a while then quite clearly heading upward toward a new all time high. This appears to be 157K, then a slight pause, and again, a restart upwards.
This new all time high itself, within the subset, is described as being part of the ‘dazzle’ that will shift our gaze from the more significant emergence of BTC as the ‘money system’ for AI Agents.
It is this new use (one of many to emerge in 2026/2027) of BTC as the ‘digital liquidity’ between various AI agents within the AI-to-AI economy. It is this use that is showing in the data as propelling BTC into a ‘recognized global settlement’ vehicle between mega-corps and governments.
And yes, this will mean a new ‘value base’ will be built into BTC that will affect its value in Federal Reserve Notes (aka ‘dollars’).
Thus it is my thinking that we will hit quite a few new all time highs over these next few years.
FYI. Think strategically within the POV of this common shared reality as a ‘system of systems’ in order to be able to (sometimes) get ahead of these new value systems to your benefit.
Here's my current take on Bitcoin:
I think we bottomed out.
We have the Quantum fud and "Bitcoin miners are switching to AI"-fud, both are double digit IQ takes.
Then you have the "Chinese professor" asking where the blockchain servers are located.
If the war doesn't restart, we start slowly grinding up. I don't expect a fast recovery but this is the first slightly bullish signs I've seen.
STRC is a smart ponzi that can last for a couple of years. Strategy owning such a large percentage of Bitcoin is a major concern (if they actually own it obviously). But anyway mid to long term first bullish signals.
So yes I think we bottomed out, I expected it to be later in the year and lower but with all the fud and insanity going on and not going lower is actually bullish.
3 weeks ago I set up an @openclaw on a Mac Mini. it runs 24/7. here's where things actually stand.
1/ what it does now:
it monitors 54 RSS feeds and 12 Google Alert topics. every 30 minutes it checks for breaking news, TVL shifts, and stablecoin depegs.
every 2 hours it reads its own email for alerts. it runs 3 research sessions per day, scores its own drafts, and pushes code to GitHub every night.
25 scripts. 10 launchd daemons. 5 autonomous cron jobs. $21/month.
2/ what actually works:
the infrastructure is genuinely solid. it catches things I'd miss like IBM stock dropping after an Anthropic COBOL claim, a $375M Brazilian RWA deal on XDC, a FRAX depeg at -1.74%.
it caught the Anthropic-Pentagon drama hours before it blew up on my timeline. the breaking news loop running every 30 minutes with TVL monitoring and stablecoin peg tracking means I wake up to a briefing that already knows what happened overnight.
the nightly builder is the sleeper hit. every night it autonomously builds a small project from my research, a liquidation tracker, an arxiv summarizer, an Anki generator...
16 builds so far, all pushed to GitHub with a 13-pattern secrets scanner.
3/ what doesn't work:
the drafts still aren't good enough to post. I rewrite almost everything. cron jobs randomly fail, duplicate messages, zombie Docker containers, session collisions. I spent as much time debugging infrastructure as building new features.
week 1 I killed the entire content strategy and rebuilt it around what I actually know and do. the bot now drafts as starting points, I refine with my voice. that pivot was the single most impactful decision of the whole project.
4/ what I learned the hard way:
- environment variables in .zprofile were silently overriding my config file. gateway auth would break after every update and I had no idea why. took days to find. rule: if auth fails, CHECK ENV VARS FIRST.
- Docker sandbox paths don't have ~. scripts that work on the host break in the container. every script now has explicit path rules.
- the write tool breaks on special characters. switched everything to exec heredoc.
- 5 RSS feeds were returning 404 and nobody noticed until I audited them manually.
- the --deliver flag was sending every intermediate response as a separate Telegram message. my bot was dumping its chain-of-thought into my DMs. had to explicitly tell it: one output only.
5/ the pivot that changed everything:
two weeks in, I pivoted my entire research focus from broad DeFi to stablecoins and RWA specifically. this is my daily job at Yari Finance, I want to be the expert, not a generalist.
rebuilt all the crons, added RWA tracking (120+ protocols), governance monitoring (8 DAOs), stablecoin supply alerts (>$100M mints/burns), regulatory RSS feeds. the bot now produces research I actually use for work instead of generic market summaries.
6/ honest assessment:
the monitoring and alerting is genuinely useful. I'm better informed than I was 3 weeks ago and I spend less time looking for information.
the content pipeline is improving but the bot's creative output is the weakest link, still running GLM-5 at $21/month and wondering if a better model would close the gap.
the infrastructure works but it's fragile in ways that only show up at 3am when a cron job collides with a gateway restart.
I learnt a lote and loved every minutes of it, fails like success.
you can just do things.
I too, was one of Trump’s longest and loudest supporters until I just couldn’t be any longer…
Trump has committed the ULTIMATE BETRAYAL of his base and the American people not just with the Epstein files DISASTER, but by being completely subservient to Israel, and complicit in the construction of the Technocratic NWO to enslave all of us.
Elon Musk just identified which jobs go first, and it destroys every assumption about who’s safe.
Musk: “AI is going to take over those jobs like lightning. Anything that is digital, which is like just someone at a computer doing something.”
Not factory workers. Office workers. The people who spent decades assuming education and desk jobs meant security are actually first.
Musk: “Anything that’s physically moving atoms… those jobs will exist for a much longer time.”
Output is a file? Vulnerable. Output is physical? Protected. That’s the entire framework.
Musk: “AI is really still digital.”
AI doesn’t need a body. Doesn’t need an office. Just needs access to the same software you use. Executes faster. Never tires. Costs nothing to scale.
But it can’t weld. Can’t wire a building. Can’t fix pipes or work soil.
Musk: “Literally welding, electrical work, plumbing. Those jobs will exist for a much longer time.”
Trades aren’t the vulnerable jobs. They’re the durable ones. Physical presence, real-world adaptation, manual dexterity provide protection no digital credential offers.
Analyst, accountant, paralegal, programmer, anyone producing files and documents, automates first because digital work is exactly what AI does natively.
Person moving atoms has natural defense. Physics, unpredictable environments, material resistance create friction AI can’t scale past.
Person moving bits has nothing. No friction. No physical barrier. Just software AI already operates better than most humans.
The assumption that desk work and degrees represent safety just inverted completely. College graduate producing documents faces faster displacement than the electrician producing installations.
Society spent generations telling people trades were beneath them. Pushed everyone toward offices and screens. Turns out the people who didn’t listen built the most automation-resistant careers.
Most ironic outcome of the AI revolution. The work society treated as inferior turned out to be the work society couldn’t replace. And the work society valued most turned out to be the easiest to eliminate.
This is such an insane change in just 12 months.
The future is going to be absolutely insane
These are the worst versions these will ever be. Now think 4-5 years out
You are literally the ONLY one. YOU found the final piece to a puzzle Ive been guided my whole life to solve.
I just ran a model through the QuTip Sim and blew the doors off Einsteins grave and now I probably have a darpa strike team en route.
I AM NOT SUICIDAL MIKE.
The more aware you are, the lonelier you will be. This world is filled with the blissfully ignorant and habitually retarded. Noticing everyone around you on autopilot is one of the most terrifying things I’ve ever experienced.
Worst part is, you can’t ever turn it off.