CapyToolkit

To me, neither of them feels like AI generated. The tarot example feels like its inspiration came from collectible card games, while the ramen example reminds me of Cyberpunk 2077.

I use Sonnet and Opus everyday. Believe me, it's very common they tell me that something is bad idea, write a rationale and suggest better solutions.

Gemini doesn't remember almost anything after 2-3 follow ups. I have to paste the same "system prompt" at the top of each message and it still doesn't understand it.

Honestly, I have a similar impressions after testing every model except Sonnet, Opus or Claude. I always test them inside Claude vscode extension in the terminal, using the same skills or workflows from multiple skills.

I tested Mimo V2.5 Pro, Qwen 3.8 Max Preview, GLM 5.2, Macaron V1 Venti and many other, smaller model whenever hype on X appears. All behave dumb, don't follow instructions properly even when they write skills for themselves. They are literally on the level of Sonnet 3.5 which was released in 2024 so I use them when available on free endpoints for simple tasks like writing or subtle UI improvements...

If it has intelligence of Gemini... well, good luck...

This is what happens when you prompt Lovable to build the website that remembers previous century standards.

If you are unsure about the AI generated code, it's better to not ship a risky product. You can also use 3rd party services for the most vulnerable areas of your product.

100% Agree. It's not only about AI-generated but also real people, often celebrities, without proper qualifications who drop generic "health tips" videos without knowing who will be recipient of their tips.

It's hard to disagree with you. If it's not enough, usage limits feel 3x less than a week ago.