LOL, no, dumbing down was when I paid two months of subscription with the model literally struggling to write basic functions. Something Anthropic eventually acknowledged but offered no refunds for. https://ilikekillnerds.com/2025/09/09/anthropic-finally-admi...
I care A LOT about the details, and I couldn't care less that they're cleaning up terminal output like this.
This feels a bit like when some Hubbers broke off to work on PlanetScale, except without the massively successful, proven-to-be-scalable open source tool to build off (Vitess).
If you're approaching this problem-space from the ground up, there are just so many fundamental problems to solve that it seems to me that no amount of money or quality of team can increase your likelihood of arriving at enough right answers to ensure success. Pulling off something like this vision in the current red-ocean market would require dozens of brilliant ideas and hundreds of correct bets.
This is true of the CLIs that start with `xcode` but not of the CLIs that start with `swift`. As `swift-format` and `swift-test` have come into their own, they're just as reliable as any other language ecosystem. And the difference is indeed staggering. I wrote this guide last summer on extracting all your app's code into a (nonsensically necessary) Swift package dependency simply so you can test it with Swift Testing https://justin.searls.co/posts/i-made-xcodes-tests-60-times-...
That’s why you should break out all of your code into SPM packages/targets. The workspace code only really needs to be the entry point, lifecycle and maybe target-based dependency injection (if you’re into that) or environment config since your SPM dependencies don’t know about your projects preprocessor macros (I.e. `#if DEV` `#if APP_STORE` etc.).
This is madness. Some stories actually have good guys. I don't know Adam directly, but we have plenty of second degree connections. I've benefited immensely from his work, have never heard anyone say a single negative thing about him, and I genuinely believe he's done more to push the web forward with Tailwind than the larger players have done (certainly more than Facebook did with React and Google has done with Angular/AMP/etc).
Reflexively assuming that unanimous positive sentiment towards someone is itself an indication of a problem is exactly the reason people are writing posts as recently as (double checks) _yesterday_ titled "65% of Hacker News Posts Have Negative Sentiment, and They Outperform" https://philippdubach.com/standalone/hn-sentiment/
May I humbly suggest taking a breath or two? It is extremely taxing mentally to select strangers to tell you don’t trust them in an imaginary crisis. (Especially ones on a tech discussion board! Especially just because they noted there were no negative comments and only fawning ones! Especially when you think fawning feels fine in a crisis!)
May I pull you aside and suggest you take a few breaths yourself? If you're finding typing half a sentence on a keyboard taxing, perhaps consider getting some support.
POSSE Party (http://posseparty.com) supports syndicating YouTube Shorts and Instagram reels, but trying to syndicate longer form video just didn't make sense IMO
I created POSSE Party because I had similar concerns. Truncation and spacing are highly customizable. You can add a posse:post sidecar element containing JSON that formats exact presentation for each platform exactly as you want it. The built-in truncation can be configured at the account level. And how you count characters, naturally, differs by platform, which the app handles pretty well.
I care A LOT about the details, and I couldn't care less that they're cleaning up terminal output like this.