Pinned Tweet
Imagine thinking about your childhood memories and seeing them unfold around you in VR.
Which tech CEO could actually make this happen?
🤖 Made with AI
"Member of Technical Staff" level interview question:
An AI agent calls an external API and times out.
You don't know whether the API executed the action.
Should the agent retry?
How would you make the operation safe?
Gaurav retweeted
I don't understand why OpenAI investing in computer-use models?
What are some real-world use cases for computer use beyond the browser?
I don't understand why OpenAI investing in computer-use models?
What are some real-world use cases for computer use beyond the browser?
Gaurav retweeted
If your secret keys get exposed on GitHub through a .env file, is rotating them enough?
Asking for a friend.
Gaurav retweeted
maybe a dumb question...
why no comparison with Gemini 4 Argon?
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
If your secret keys get exposed on GitHub through a .env file, is rotating them enough?
Asking for a friend.
maybe a dumb question...
why no comparison with Gemini 4 Argon?
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
Where should you store an auth token?
xitter.cf/Leapofcode/status/2113…









