This is my first campaign pushed on Uneed and I have to say. I didn't pay for boost. I set it some time ago to see how it works. And it's actually quite nice. See my app here: uneed.best/tool/blur-face…

What shocked me in iOS development 😲 Now imagine Android Studio removing device mirroring because of this. It’s really hard to bypass.

This post may be shocking to many, but this is how it works today - especially with AI. If you’re working on a problem, check what you can do with the tools available right now. If it’s a bigger challenge - really, a solution you want to build - try a few different AI models and

The amount of crap I get for putting out a hobby project for free is quite something. People treat this like a multi-million dollar business. Security researchers demanding a bounty. Heck, I can barely buy a Mac Mini from the Sponsors. It's supposed to inspire people. And I'm

Anthropic bans their subscription from being used for API credits in ClawdBot, then forces a name change so it doesn’t sound like Claude, then Kimi K2.5 drops, open source, and is supposedly BETTER than Opus 4.5 anyways… Couldn’t have set themselves up any worse than this The

Funny thing. For the first time I reached quota limit in Google Antigravity. While everyone is sharing info about reaching limites for Opus - I'm lately using Gemini 3 Flash. And for daily tasks - it's so awesome. I prefer it in many cases more than Gemini 3 Pro. Daily tasks - no

Hey Cursor 👋 Why did you remove the number of requests used per model. That was super helpful. We are able to see tokens used, but some models are taking x2 requests and that info was always great as a reminder.

Zapraszam jutro od odsłuchania. Co przekręciłem biorę na siebie. Pierwszy raz mogłem sprawdzić się w tej formie, ale też nie sadziłem, że będę pierwszym gościem nowego formatu 🙈

Zapraszam do posłuchania rozmowy u Mateusza! ☺️

I didn't expect such a big difference from Codex 5.2. Codex-5.3-high shots today 😲 I was shocked it just did that huge tasks in one-shots - with writing tests, running tests. Opus in Cursor is x2 more expensive but for me - I like it for planning more, preparing, talking

In Android Studio (latest Canary), the default model is still Gemini 2.5. It may looks that this "Chat" (agent) in AS is abandoned. But it's not. Actually the agent inside Android Studio is getting better and better. I’m not sure what Google’s strategy is, but currently they’re

If Codex is not working well for you. You could be rerouted to different model and you need to pass verification at chatgpt(.)com/cyber github.com/openai/codex/i…

Is this another no from Apple for "vibe coding"? 👀

Rozmowa z Mateuszem od dzisiaj również na Spotify 🎧