Watch Gemini 2.5 Pro implement a landmark Google DeepMind research paper. 🕹️ It codes the reinforcement learning algorithm, visualizes the training live and even debugs errors. ↓

Really appreciate you all included the errors and how to potentially fix them. I am working on a similar workflow and figuring out how to provide error more efficiently as feedback to agents.

💡 Learn how Reinforcement Learning can boost your trading performance! In this free Substack article I share full code of a trading algorithm based on Reinforcement Learning that beats other Machine Learning models as well as simply buying and holding the stock.

We'll you just saved me time! is faster to type than

The future of AI x coding is here. Gemini 2.5 Pro not only writes reinforcement learning algorithms — it runs them, visualizes training, and debugs in real-time. 🧠🕹️ Watching this feels like a glimpse into the next generation of engineering workflows.

You have a better product than Open ai. Its time to focus on usage

Can you guys improve the UI? Most of the time it just renders badly when it comes to changes, syntax, conversation names and also why isn't Rmd and md code blocks doesn't have syntax highlighting.

Nice RL feedback loop. Video did a good job showing how this works

The ability to debug errors in real-time is mind-blowing.

Absolutely mind blowing. I think @Google should build an IDE like Cursor.

code(44).html have you tried 44 times

that's pretty incredible but is it repeatable and scalable