I help devs use AI tools to ship faster. Full-time iOS engineer & indie builder · SwiftUI enthusiast.
Istanbul
Joined May 2020
- Tweets1.4K
- Following138
- Followers43
- Likes330
Need to go offline on each big model release
Preparing for endless posts about how [insert new GPT model] is AGI and "I built an AAA game in an hour". Better going offline for a few days until the hype parade has finished and everyone realises it's still sh*t at frontend design and software architecture.
4
Today was my last day being unemployed.
I am so thankful for the time I got to spend there. I couldn't be more thankful for the time I spent and the connections I made.
Will be taking some time off as I prepare for my next thing. I'll share more soon :)
11
made a Mac app that moves the cursor with hand gestures in front of the camera. It works, but my arm died after 2 takes of this video :)
44
I hope that Anthropic and OpenAI will go bankrupt because what is happening is not honest. They give us the REAL inteligence and than for economy they nerf models and cut usage limits. This is not serious for any type of real job.
9
Looks like Claude links parsing is totally broken on other languages than english, <cite…> everywhere in text @trq212
25
ChatGPT is unusable, I have 2 accounts with different chat history and I can't switch. Forced to use claude for now
30
Idk but Codex 5.6 is the most inefficient model currently. Hundreds of millions tokens for same tasks that before cost me less than a hundred
17
I had different accounts for ChatGPT and Codex and had 2 apps. Now I have one app and no idea how to connect second account in the same app. My workflow broke. The worst release of Codex/GPT team in a year. @jxnlco @Dimillian @thsottiaux
1
54
Something feels wrong with GPT-5.6. It’s not token-efficient at all.
@thsottiaux @Dimillian, I spent the whole day doing productive work and used around 20M tokens. Then I ran the new version, and it burned through 50M tokens in just half an hour.
That’s a problem.
122