#SQL user-defined functions are now even more user-friendly and powerful Check out the enhancements we’ve made to keep queries simple while enjoying strong type-safety http://
bit.ly/3KWEBpD
CODE
-
SQL user-defined functions enhanced with better usability and type-safety
By
–
-
Training AI Models Using Hugging Face Open Source Tools
By
–
Trained using 100% off the shelf tools from @huggingface and models and datasets hosted on the Hub
-
Task Storage in Pinecone for AI Agent Context
By
–
More or less. It’s also storing task/result in pinecone and tapping into it for context in future tasks.
-
Building AI Systems Shouldn’t Be This Accessible
By
–
Yeah, I kind of feel like it shouldn’t be this easy to build this…
-
LangChain Task Creation and Reprioritization Loop Architecture
By
–
Each task is langchain, but the task creation and reprioritization loop is custom
-
Autonomous AI Agent Building Task Lists via Web Search
By
–
It is. But the capability is more than anything I’ve built before (granted not saying much). Right now it’s searching the web to continue building a task list for itself based on an objective, but only a few lines of code away from being able to email people and hit APIs if
-

Configurable AI objectives raise safety and open source concerns
By
–
Ohhhh, so I can set ANY objective (eg. make the world a better place).
— Yohei (@yoheinakajima) 27 mars 2023
Don't think I should open source this one… 🥴 pic.twitter.com/UEWmyGuDqKOhhhh, so I can set ANY objective (eg. make the world a better place). Don't think I should open source this one…
-
Best AI Tools for Accelerating Coding and Development
By
–
What is the better AI tool for accelerating your coding & development?
-
Deploy H2O Wave Apps to Hugging Face Spaces in Minutes
By
–
With #HuggingFaceSpaces, you can create and deploy ML-powered demos in minutes. Check out the latest blog from @unusual_code showing how easy it is to deploy your first @h2o_wave app into Spaces! #MachineLearning #ML #AI #DataScience @h2oai
-
Storing Task Results in Pinecone for Context-Aware Execution
By
–
Thanks! I’m storing every task/result pair in pinecone and pulling 5 most relevant ones as context when executing each task (or trying to).