tae

ChatGPT Images 2.0 can generate really cool UI - either for your apps or games. Here I asked it to generate UI for game based around 'Falcons' and for a random health app. It generates everything PERFECTLY and usable in your actual game/app. The only thing I HATE about it is it can't generate transparent images - which is a degrade from the previous version of it's image model. Experimenting more, stay tuned!

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.

Peguei um Uber que tava mandando áudio pra um brother no WhatsApp falando que precisa ter um GitHub com projetos bons pras consultorias te chamarem Não sei se isso é um sinal de topo ou de fundo pro mercado

How can we autonomously improve LLM harnesses on problems humans are actively working on? Doing so requires solving a hard, long-horizon credit-assignment problem over all prior code, traces, and scores. Announcing Meta-Harness: a method for optimizing harnesses end-to-end

Would really appreciate if you could do something about the, at this point, obvious degradation in Opus 4.6’s performance? Overnight for me and apparently countless others, Opus went from being truly next-level to being a bumbling IDIOT, and I mean that. Lying about completing tasks, just…stopping mid task, making simply idiotic mistakes which I the. Have to literally spell out in order to get it to fix, on and on. And this is happening in both Claude desktop (in just normal chat), AND in Claude Code. I sure got the $200 a month I was paying for at first, but the last week has been truly unbearable.