Is complex prompt engineering a trap for advanced AI models? 🤯 My new paper finds that the "best" prompts for a model like GPT-4o actually HARM the performance of GPT-5. I call this the "Prompting Inversion" effect. Here’s what I discovered 👇

They made Paul Rudd in makeup play a paleontologist and thought we wouldn't notice.

Santa says 67? Why would santa say that?

Is Dan Brown a time traveller? - theft at the louvre - worldwide virus - ai eating the world

producthunt.com/products/vellu…

hi

What would this be about?

No one from Anthropic is helping me with these issues i am seeing since yesterday. Has anyone solved this themselves?

Daily Aches 🥹

It's been a while since any new JS/CSS/React Frameworks dropped.

The whole point of Yuji's existence was to be a vessel that can contain Sukuna. But even Megumi was able to contain Sukuna. So there was no point in kenjaku biohacking cursed womb vessels. Why did Gehe even write the character of Yuji?

claude is down? how am i supposed to work now?

claude is down ;(

Every AI slop post on socials: - This is not X, this is Y - it's not X, it's Y - this does not X, this does Y - it's not about X, it's about Y

My dear Claude is down today. Pls leave a msg to lift his spirits 🙏