obviously xitter.cf/zamdoteth/status/21142…
Sam T retweeted
There should be an app where you upload your bills and bored billionaires swipe right to pay them.
My daughter wants gaming Pc.
My @OpenAI Dot is searching thru all the local listings on Facebook marketplace to find me the best deal.
What a time to be alive!
My social media scheduler verifies its own work by using itself to post promotional content about itself
Give your agent a way to verify its work. This can dramatically improve the quality of output.
With this process in place, Claude Code was able to write 90%+ of its code itself. When generating software at a faster rate than you can review it, the bottleneck shifts to proving that it works. @bcherny and team invested enough in verification, we've been able to move fast while maintaining stability.
Code reviews aren't going away, but you need to think of it differently. One human reading through line-by-line is no longer going to work as a gate, it needs to evolve into a multi-layered verification system, built with fast deterministic feedback loops for your agents.
This is where e2e tests, feature maps (as @poteto has been advocating), property tests and multi-agent adversarial reviews come in. These all provide opportunities to catch errors early and fix them before things get out of hand.
You don't have enough eyeballs for the amount of code being written so your focus needs to be on product intent, risk assessment and evaluating evidence rather than reviewing code. Delegate the code checking work to your automated tests, scale your approvals based on risk, and turn your test failures into living evaluations. This approach helps maintain speed without losing reliability.
Let the agents do what they do best and let you focus on what makes you irreplaceable: judgement, direction, and ownership. We tried to capture how we handle code review and verification in this writeup. Hopefully it's helpful.
It may be called Mail Cheap, but this design is premium @marclou 🤩
I vibe-coded beehiiv, and it's 83% cheaper.
✨✨ Introducing MailCheap.ai ✨✨
Everything you need to run a newsletter...
✍️ Editor
📅 Scheduling
📈 Stats
🌐 A website for every issue
🛡️ Deliverability guardrails
🔗 Send from your own domain (and keep your reputation)
And it's not a dinosaur tool:
+ It's open source; you can run it for free
+ It's agentic; everything in the UI is available to your AI
Import from beehiiv, Substack, or Mailchimp in 2 minutes.
You pay for the emails you send, not for dormant subscribers. From $19/month.
Oh, and no "Powered By" badge at the bottom of your emails.
You can ask Claude or Codex run daily checkups of your SEO, your funnel, your security etc and proactively fix any issues it finds.
Dots caused a production outage on my saas after 1.5 hrs of usage.
Codex has not done that in the last 9 months of usage.
I’m building a saas without ever looking at it.
Opus 5.5 runs it with the main task of improving it every day using real data/users/traffic.
I get one Telegram message every day which says “Did we improve? Yes”.
One of my friends knows everything about the latest harnesses, tools, configs, skill setups.
He makes $0 MRR
GPT-6 Sol in Ultra mode is nerfed. It’s making elementary mistakes.
We need to be able to trust these models.











