roo_code's profile picture. A whole dev team of AI agents in your VS Code.

Roo Code

@roo_code

A whole dev team of AI agents in your VS Code.

Google is already stretching context windows to 1M and 2M tokens. What comes after? @OfficialLoganK talks about the 100M-token frontier, the innovation it demands, and why “great scaffolding” matters most for developers. We are excited to see what Gemini 3 brings! Full podcast:…


The new open source MiniMax model is available for free in the OpenRouter and Roo Code Cloud providers for a limited time!

MiniMax’s M2 achieves a new all-time-high Intelligence Index score for an open weights model and offers impressive efficiency with only 10B active parameters (200B total) Key takeaways: ➤ Efficiency to serve at scale: MiniMax-M2 has 200B total parameters and is very sparse with…

ArtificialAnlys's tweet image. MiniMax’s M2 achieves a new all-time-high Intelligence Index score for an open weights model and offers impressive efficiency with only 10B active parameters (200B total)

Key takeaways:
➤ Efficiency to serve at scale: MiniMax-M2 has 200B total parameters and is very sparse with…


Yup - it gjves better, faster, and cheaper reviews than most humans we know.

Just tried @roocode PR Reviewer Agent and it really works. 1- Cloned anthropic courses repo from github 2- In the notebooks, as markdown notes, it tells to use "claude-3-haiku-20240307" and prompt is "Tell me a joke" 3- I changed the model to:"claude-haiku-4-5-20251001" and…

CloudTrader4's tweet image. Just tried @roocode PR Reviewer Agent and it really works.

1- Cloned anthropic courses repo from github
2- In the notebooks, as markdown notes, it tells to use "claude-3-haiku-20240307" and prompt is "Tell me a joke"
3- I changed the model to:"claude-haiku-4-5-20251001" and…
CloudTrader4's tweet image. Just tried @roocode PR Reviewer Agent and it really works.

1- Cloned anthropic courses repo from github
2- In the notebooks, as markdown notes, it tells to use "claude-3-haiku-20240307" and prompt is "Tell me a joke"
3- I changed the model to:"claude-haiku-4-5-20251001" and…


Building scaffolding for LLMs is powerful, but it has a cost in development time and trade-offs. Google DeepMind's @OfficialLoganK discusses this developer pain point and how smarter models are changing the game once and for all. Full conversation on the Roo Code podcast :…


Roo Code works while you nap.. :)

roocode's tweet image. Roo Code works while you nap.. :)

AGI will be an Experience, Not a just a Model. How will we know when AGI is here? @OfficialLoganK of @GoogleDeepMind predicts it won't be a single event, but a gradual realization through a product that just works. Full conversation on the Roo Code podcast :…


Awesome to have @OfficialLoganK on the Roo Cast yesterday. And if anyone in the future does in fact want to drop a big announcement on our podcast, please DM 🙏

Logan Kilpatrick says Gemini 3 is coming soon, and the positive vibes are exciting A year and a half ago, few cared about Gemini models; now trust and excitement are earned across the ecosystem It shows how fast perception and usage can turn "so soon soon"



United States Trends

Loading...

Something went wrong.


Something went wrong.