SweetSoftPillow

They were available, just rate limited.

It's interesting why the author used weaker models (like Grok 3 when 4 is available, and Gemini 2.5 Flash when Pro is), since the difference in coding quality between these models is significant, and results could be much better.

LLM will write lowercase if you prompt it to do that

It doesn't show that. You can prompt AI to omit capital letters and punctuation.

I had these issues with Windows, but with Linux Mint it works perfectly.

I feel like this is very logical way to do things. Test hypothesis on small model, play around, get it working, apply findings to big model.

OpenSim Core - open-source software for simulating the physics of movement in biological systems via musculoskeletal modeling.

It's a whole new modality, and it seems we do not have output devices (yet)

Check "misguided attention" repo somewhere on GitHub

No, just check their models Knowledge cutoff dates

You can't.

It must have something to do with the way your wife is prompting. I've noticed this with my friends too. I usually get working code from Gemini 2.5 Pro on the first try, and with a couple of follow-up prompts, it often improves significantly, while my friends seem to struggle communicating their ideas to the AI and get worse results.

Good news: Prompting is a skill you can develop.

Switch to Gemini 2.5 Pro, and be happy. It's better in every aspect.

What exactly surprises you? You should try Gemini 2.5 Pro in Google AI Studio. Set the temperature to around 0.3, and in the system prompt, tell it to only edit exactly what you ask for and nothing else.

This model works really well. For example, simple things like [1], [2], and [3] can apparently be generated with just a couple of prompts.

[1] https://koreanrandom.com/en/games/through-the-space/

[2] https://koreanrandom.com/en/games/tanchiki/

[3] https://koreanrandom.com/en/games/sharik/

According to the author, these were made with Gemini 2.5 Pro without any manual coding by a human.

Cursor isn't as powerful as Gemini in AI Studio because AI Studio gives you full control over the model's settings and how it processes code.

Plus, the massive 1 million token context window is incredibly helpful for working with large codebases. You can use tools like code2prompt and repomix to feed all the necessary context into AI Studio from the clipboard for those projects.

You definitely underestimate kids and overestimate adults.

Aider is written with AI, you're welcome.

https://github.com/mufeedvh/code2prompt https://github.com/yamadashy/repomix

Gemini added their multimodal Flash model to Google AI Studio some time ago. It does not use Imagen via tool, it's uses native capabilities to manipulate images, and it's free to try.

Since "Manus" is a registered trademark, you should probably change the name as quickly as possible to avoid legal issues with the original trademark holder. At the very least, you could remove the "M" to avoid directly copying it while still maintaining recognizability.

Can we run it in Chrome?

r1 + Claude 3.7 when?