-----BEGIN EC PRIVATE KEY----- 4 -----END EC PRIVATE KEY-----
-----BEGIN EC PRIVATE KEY-----
Joined June 2011
- Tweets2.2K
- Following308
- Followers483
- Likes3.7K
Pinned Tweet
The agent economy is being built one-sided: wallets, cards, and browsers — everyone teaching agents how to spend.
Almost no one is teaching businesses how to accept.
That’s what I’m building. It’s called Bubblio: you put a door on your product, and agents can find it, ask questions for free, and buy the real thing — a firm quoted price, one tap of approval from their human’s phone, and the money lands on your own Stripe.
Early days — three doors are open. You can knock: bubblio.dev
The Neopets page surviving a new exploit since 2004
Hold tight, embrace yourself and talk with a real engineer about the news.
Stay safe
‼️ BREAKING: 8 Private keys belonging to eMudhra intermediate certificate authorities (CA) have been compromised.
Chrome and Firefox blocked the affected certificates within hours. Go, NSS, and other software have issued fixes.
Full details - thehackernews.com/2026/10/ei…
Thinking about making a group of people to talk about Hermes and @NousResearch in my city to share tips and tricks and projects
That is why I like my error-driven development
Why are you still using pull requests?
Is it for code review?
If so, do you really think your or your colleagues catch bugs and mistakes that an Opus 5.5 or Fable or Astra won't find? You can literally spawn all three of them and have them check four times each.
(Also, don't tell me you don't have a "stamp plz" Slack channel or group chat somewhere.)
Is it for knowledge sharing?
Surely there's better ways for that now than the PR, no? We have models that can generate explainer videos, presentations, podcasts, games, quizzes, walkthroughs, ... for any piece of code it can reach.
Is CI the reason?
Well ackshually, CI means continuous integration and its original meaning is the *opposite* of having long-lived branches and PRs.
But, leaving that aside, your agents are hopefully already running the tests before they push something, and hopefully they can run as long as they want and don't block you so they can run the whole test suite and generate "irrefutable proof" and end-to-end demo videos and so on... And so they run the tests and confirm and then you push to a branch and everything runs again and then you merge and then it runs again? That doesn't make sense, does it?
Maybe you work in open source and you accept contributions, in which case I can't speak to the value of pull requests. It's been 2 years since my last OSS contribution. But from what I heard, the time of the PR is coming to an end in OSS too?
I honestly don't get why people still stick to PRs.
With agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.
Don't slow yourself down by having all the changes pile up in a PR.
Introducing epstein.md 👋
A 927,400+ Character .MD File that's specifically trained to skip every vibe coded AI Slop design principle.
- no box shadows
- no emojis
- no '🟢 LIVE ' badges
- 0 blue/purple gradients
& religiously ignores 350 most common AI words (delve, vibe, seamless ...)
It's the result of 11 months of 8 hrs/day Twitter doomscrolling and constant additions to the codebase of our vibecoding ui.
Wholeheartedly hoping this finds the most design-needy indie hackers.
One thing I notice about using agents for testing is that they are not reliable about rules.
I have been testing an app that uses PIN to unlock without problems and today my agent tells me that it can’t since it is in their rules from Anthropic
These kind of changes break flows
Medians of 3 runs, warm iOS simulator: finding the path took 6.7 s and $0.0005 in model calls. The test it wrote runs in 6.6 s with $0 in model calls (it still needs a Mac with a simulator).
iOS simulators for now (Android is experimental). Bring your own TypeSafe key. The first run on each simulator builds WebDriverAgent with Xcode.
npm i -D jevvium
MIT: github.com/AndresCarreonDiaz…
A feature ships with no Appium test yet.
I built jevvium: write the test plan in plain words, and it follows it on an iOS simulator and writes the Appium test. Real footage, edited for length.
github.com/AndresCarreonDiaz…
Update: the slow weekend got out of hand.
Jev is a decision model. It reads text and picks between options. It can't see images at all.
So I tried to give it eyes. What worked, what flopped, and what I'm still building 🧵
Next: app screenshots.
Flat colors, rectangles and text are exactly where the retina is strong. That could let jevvium tap "the blue login button" from pixels alone. No accessibility tree, no vision model.
Everything is open, failures included. Every number in this thread has a script behind it:
github.com/AndresCarreonDiaz…
