sure, I don't know though how much Gemma and the flavor of Gemini they are using there have in common though.
LLMS
-
Local Model Comparison Issues with Llama and Alternatives
By
–
When trying them out locally, they usually compared favorably to Llama etc. What were the issues you were having?
-
LangChain OpenAI Responses API Integration Guide
By
–
Docs: …
https://langchainjs-docs-git-dq
bd-oai-responses-langchain.vercel.app/docs/integrati
ons/chat/openai/#responses-api
… -
Google Releases Gemma 3: 27B Multimodal Open Source Model
By
–
Very excited to see the release of Gemma 3, the latest in our open source models. It is only 27B parameters, is multimodal, and has a delightful footprint that fits in a single H100 GPU, and runs really well on TPUs as well. https://t.co/SzndoMOQnX
— Jeff Dean (@JeffDean) 12 mars 2025Very excited to see the release of Gemma 3, the latest in our open source models. It is only 27B parameters, is multimodal, and has a delightful footprint that fits in a single H100 GPU, and runs really well on TPUs as well.
-
New Resources Hub for Building AI Agents
By
–
Looking for inspiration or guidance as you're building your AI agent? Check out the new Resources Hub on our website! Our Resources Hub contains guides on evaluating your LLM application, reports on the latest AI trends, and action-packed tales of how companies like @Replit
, -
NotebookLM adds citation support
By
–
NotebookLM notes now support citations as well. Earlier citations were only available in chat responses.
-
LLM-Friendly Code Copying Tool Across Any Codebase
By
–
"Copy to clipboard" but for LLMs, from any codebase. Wow, nice feat!!
-
Google AI Studio reportedly released (partial rollout)
By
–
http://
aistudio.google.com with these settings It just released so it may only be partially rolled out -
LoRAs Explained: Fine-Tuning Models with Trained Weights
By
–
LoRAs have become the standard for fine-tuning models, but what even are they? When people refer to "a LoRA", they mean a set of trained weights that can be added to a base model, like Flux or Wan2.1, to create a fine-tuned version. Check out our new guide to working with
