Congrats! Is Gemini Pro now powering Duet AI for Workspace too? Or is that still PaLM2?
SOFTWARE
-
LangChain Expression Language: From POC to Production
By
–
"LCEL provides a fresh perspective on LLM-based application development. I highly recommended using it for your next LLM project." Community member Tom Darmon wrote a great deep-dive on LangChain Expression Language (already 1.5k likes on Medium) https://
medium.com/artefact-engin
eering-and-data-science/unleashing-the-power-of-langchain-expression-language-lcel-from-proof-of-concept-to-production-8ad8eebdcb1d
… -
Flowise Hands-On Tutorial Series with leonvz
By
–
Glad to work with @leonvz for a full new Flowise hands-on tutorial series! https://
youtu.be/nqAK_L66sIQ?si
=DhAOo8Is2TSLtP6E
… -
MobileDiffusion Enables Sub-Second On-Device Text-to-Image Generation
By
–
Introducing MobileDiffusion, a novel approach with the potential for rapid (sub-second) text-to-image generation on-device. An efficient latent diffusion model with a comparably small model size, it is well suited for mobile deployment. Learn more →
https://
goo.gle/3vWqE5J -
H2O AI and Snowflake Reduce Inferencing Costs by 3000%
By
–
We recently made a breakthrough in ml model deployment with our partners at Snowflake that reduces the cost of inferencing by 3000% Check out the full story: https://
medium.com/snowflake/the-
cost-saving-benefits-of-faster-scoring-in-snowflake-with-h2o-ai-0964c8d0c3e9
… #H2Oai #Snowflake #Snowpark #Inferencing #MachineLearning #AI #CostEfficiency -
Tenstorrent Open Sources TT-Metalium Kernel Software Stack
By
–
We're excited to announce that we have open sourced our kernel-level software stack, TT-Metalium. @ojoyoshida sat down with @DavidBennett__ and #tenstorrent fellow Jasmina Vasiljevic to talk #opensource, #software and our Grayskull DevKit https://
ojoyoshidareport.com/if-nvidia-is-a
i-hardwares-goliath-wheres-david/
… -
ML Algorithms and MLOps: Beyond the LLM Hype
By
–
Amidst all the buzz and hype surrounding LLMs, we want to bring a brief spotlight on ML algorithms. Most algorithms have to do with tabular data and there are multiple steps involved in iterating and maintaining machine learning models in production. Using an MLOps platform
-
GitHub Copilot Chat improves code quality across the board
By
–
Research: Quantifying GitHub Copilot’s impact on code quality bit.ly/49dq81g Our research found that the quality of the code authored and reviewed was better across the board with GitHub Copilot Chat enabled
→ View original post on X — @marktabnet, 2024-01-31 15:07 UTC
-
RAG and expert AI orchestration
By
–
Even simpler! 🙂 It's based on RAG (Retrieval-Augmented Generation) and an orchestration system we built that calls multiple small expert AIs, each specialized in their own domain. 🙂 A bit like the analogy OpenAI published a few months ago. 🙂