Ronni P

@sama Built a fully automated, pooled football (soccer) game for friends, groups and communities. Codex allowed me to engineer it to very high level, probably over engineered even. lastmanstandingplanner.com

i would like to talk to people who have built amazing things with 5.5 that weren't possible with earlier models. i am especially interested in examples that took ludicrous token budgets. thanks.

@CiprianiRanieri lastmanstandingplanner.com

Builders only. Drop your product. No pitch. Just link

New article up for builders and product people out there✍️ open.substack.com/pub/ronnisprod…

@pbakaus This is great! Just need a drone to deliver your coffee to you!

@sama @sama why oh why couldn't this have been today. About to ship my first major prod app build using Codex and I can't run through pre-product tightening because my limit resets in a few days. 😢

To celebrate 3 million weekly codex users, we are resetting usage limits. We will do this every million users up to 10 million. Happy building!

@gsvm42 @GamewithDave You have just stirred some memories I forgot existed. Recall spending an entire summer holiday playing this.

@GamewithDave Commandos: Behind Enemy Lines

For anyone who used a computer between 1990 & 2005… what’s the one game you still think about?

@pbakaus That's my weekend then!

Impeccable 2 (my take on the most effective way to make your AI harness better at design) dropped last week. But I was so busy working on the next iteration that I buried the lede a bit. So here's a detailed post on what's new and improved: 1. CLI: npx impeccable detect. Scans your code *without need for an LLM* for 25 anti-patterns across typography, color, layout, motion, and quality. Works on HTML, CSS, JSX/TSX, Vue, Svelte, and CSS-in-JS. Framework detection, multi-file import tracking, Puppeteer-backed live URL scanning, CI-ready JSON output,--fast regex mode for huge codebases. Yes, you can built automatic PR anti-slop detection with this in a few lines of code! 2. Chrome extension. One-click detection on any page (yours, staging, production, or someone else's). DevTools panel. Live computed styles, interactive panel, on-page highlights. 3. Dramatically upgraded /critique. LLM + real time detection sub-agents run in parallel, score against Nielsen's heuristics, auto-run the detector, and open a live browser overlay so you can walk each finding in place. 4. Data-driven design performance improvements, driven by an internal eval framework that runs the same brief through frontier models with and without the skill loaded, then measures how much the output collapses into monoculture. The biggest unlock: an anti-attractor procedure that forces the model to enumerate and reject its reflex defaults before picking. Validated on gpt-5.4 and Qwen 3.6 Plus across 15 niches. Result: much more font and color diversity, sharper quality, stronger Codex support. 5. Design before code. /shape runs a structured discovery interview and produces a design brief before any code is written. /impeccable craft chains that brief into the full implementation flow. You ship a designed feature instead of a reflex card grid. 6. One name, one namespace, and 18 commands (down from 21). The skill used to be called frontend-design, it's now called impeccable. /teach-impeccable became /impeccable teach, /extract became /impeccable extract. /arrange became /layout. /normalize merged into /polish. /onboard merged into /harden. Auto-cleanup handles leftover files on first load after updating. 7. A real docs site. 18 per-skill pages with before/after demos, canonical SKILL.md inline, two tutorials, 38 rule cards with inline visual examples. Give it a try: impeccable.style

Claude OAuth problems this afternoon. Have they tried Codex to fix the issue?

@pbakaus I have been using Playwright MCP, I think cursor has a new feature that provides replays of tests you can watch which is cool too. I run lint/smoke on dev, full E2E on staging via GitHub actions. Also thank you for Impeccable, it has drastically changed how I review design 🫡

If you're using Codex (desktop or cli) as your primary driver - what is the best way of doing browser iteration/automation right now with Codex? Ideally with a visible browser in front of me (not just headless) Playwright? Some Atlas thing? Chrome DevTools MCP?

@bcherny @peter_szilagyi I've been ghosted too 👋

@peter_szilagyi Looking

Well, fuck Anthropic. I've bought a 3 month Claude Max sub to a friend as a gift. Sent it to them. 10 days later, their gift is GONE from their account. No trace whatsoever. I go to Anthropic to request a refund: - I can't it's not my gift. - They can't, it doesn't exist. Oh, and you have NO WAY to contact a person who understands the problem, you can only talk to a fucking AI whose job is to get rid of you. It just closes the convo with "End." after you explain what's wrong.

It just woke up and voila. Managed to work on a simple UI tweak across 3/4 message exchange and hit the limit. @bcherny what is going on at @AnthropicAI? Side issue, I am still waiting for support to get back to me on a previous ticket too, 8 days and counting.

This is going well. Been like it for days. Not even the Fin the AI Agent working in support is able to help with this one. Anyone else struggling?

Hey @AnthropicAI any chance you can respond to my support ticket - I have been waiting for a few days now. Fin is a cool but I don't think he's the right person for the job, in this instance.

@paulg @metapreston You can be cynical about this or just realistic as someone who is running my own thing at age 40, with 2 kids and a wife, believe me when I say it is one of the toughest things you'll ever do. Focusing in your 20-30s is the best advice, you are more self -focused and energetic.

@metapreston How can you claim it's YC dogma not to have kids when I wrote an essay about why people should? paulgraham.com/kids.html Do you just make this stuff up?

Ignore the YC dogma. Get married and have kids And work with the people who have something to lose

@mattpocockuk It almost feels lazy, like a defeated model.

Doing some experiments today with Opus 4.6's 1M context window. Trying to push coding sessions deep into what I would consider the 'dumb zone' of SOTA models: >100K tokens. The drop-off in quality is really noticeable. Dumber decisions, worse code, worse instruction-following. Don't treat 1M context window any differently. It's still 100K of smart, and 900K of dumb.

@garrytan I am currently around L6. Would much prefer to skip L7 and go straight to L8. Managing 10 + agents manually, just sounds like a Git Nightmare in the making. Wild times though.

I am coding a lot, GStack is helping me do it, but also I want you to know I was stranded in Austin the last 24 hours due to weather, and also last week my mom was in the hospital and not too lucid for most of it, so I was coding by her bedside too. She's ok now and I just visited her at home and set up her medication. I do have a full time busy job, and is it really possible for a CEO to be coding all the time? Frankly, I think it will have to be. The CEO has to set the future of the company. All companies will need to adapt to a faster world and do more. Boil the ocean. It's not about doing less and cheaper. It's about doing more and making 10x better products and services. Is 16k LOC/day sustainable for me? We're going to find out if I can manage to get to L8 software factory. I have not done it yet. But you can tell the models are about to get much much better. L8 is barely possible today, and I think I'm close. But everyone will be there soon. I want to be one of the people who helps all of you do it with me.

@trq212 Love this, I have been needing it for a while.

We just added /btw to Claude Code! Use it to have side chain conversations while Claude is working.

@jamesdevonport Great stuff James. +1 to see a demo. I think something like this might help me in the coming months.

First day tracking results from new Claude Code Meta Ad system... Being able to track every creative from CC is simply amazing, some of the creatives I would never have expected are already leading! Will be running this every day and letting it optimise the campaign as we go.

For Enterprises: The New Rules of Moats (Part 3: Enterprises) linkedin.com/pulse/new-rule…

Been talking to people a lot about defensibility of products in the current age, I wrote a 3-part blog on this a while back which I believe still holds true. Links are in the comments.

For Scale-Ups: open.substack.com/pub/ronnisprod…