Claude-4 is incredible! I’ll keep recommending it as the #1 model because the reasoning and depth it brings to coding projects is hard to beat. The challenge is that I’m building 9 projects at once right now. When you are coding daily at that scale, even the best models start to add up in cost. So I went hunting for a lighter option I could lean on in Cursor. I tried Gemini-2.5-Pro. I tried GPT-5. Both solid. Then I tested grok-code-fast-1. Here is what I found: - Way faster than Grok-4 (they were not kidding with “fast” in the name) - Free right now in Cursor - For raw speed and responsiveness, I have been enjoying it more than Gemini-2.5-Pro and GPT-5 If you are coding on a budget or just tired of waiting around for long completions, this is worth trying. I will keep sharing how it holds up as I push it across my projects. If you try out the model, I'd love to hear what you think about it!

Hello, Can someone please help with this issue: Getting an error when creating a basic agent with GOOGLE_GENAI_USE_VERTEXAI=TRUE Followed all gcloud cli steps to authenticate and configure project, enable Vertex AI APIs etc., HTTP/1.1 401 Unauthorized" 2025-09-17 21:41:46,793 - ERROR - adk_web_server.py:1076 - Error in event_generator: 401 UNAUTHENTICATED. {'error': {'code': 401, 'message': 'API keys are not supported by this API. Expected OAuth2 access token or other authentication credentials that assert a principal.

Hi all, I'm struggling to achieve token-by-token streaming with the Vertex AI streamQuery API (streamQuery?alt=sse). Both my Python script (using requests.post with stream=True) and curl command return the full response after a delay (~4.3s) instead of streaming token-by-token. I’ve also tried integrating with a Next.js frontend, but the output still appears all at once. Has anyone successfully implemented token-by-token streaming with this API? Any working examples for Python, curl, or Next.js would be greatly appreciated!

VIEW RECORDING - 125 mins (No highlights) Key Takeaways - Brandon completed an agent-to-agent (A2A) tutorial for ADK, showcasing integration with CRI, LandGraph, and ADK agents - Participants shared diverse AI projects, from video generation to fantasy football automation - Discussions on PDF processing, database integration, and deployment strategies for AI applications - Updates on new features in Crew AI and comparisons with ADK functionality Topics ADK Updates and Tutorials - Brandon finished an A2A tutorial for ADK, demonstrating integration with multiple agent types - New ADK deployment video coming soon, showcasing API endpoint exposure and Cloud Run integration - ADK's strengths in chat functionality, but limitations in multi-agent collaboration compared to Crew AI Participant Projects - Mitch: Working on a tool for generating video content using AI, transitioning from Airtable to a custom software stack - Juan: Deploying AI infrastructure with LLMs and RAG systems for a client, exploring Llama Index for tabular data handling - Ty: Developing custom software solutions for business needs, including inventory management and POS systems - Marc: Creating a video game-themed customer service and inventory management system using ADK and Docker

Hi everyone, I just finished ADK Masterclass. If you’re: - Just beginning now - Already working through it Let’s connect! (LinkedIn: https://www.linkedin.com/in/osamatech786) Also, if anyone needs help with following thorough Masterclass, feel free to ask here & I’ll do my best to assist. Thanks!