Felt opinionated and I wanted to introduce the framework first (it also was a bit buggier). Cleaning up the version w langchain and will share when ready.
CODE
-
Generalized AI capabilities for organizational management applications
By
–
I personally am most curious about the generalized capabilities, and using it to manage orgs – but I’ve heard ideas around robotics, bio, and coding that are interesting.
-
Using GPT4 to Generate Baby AGI Research Papers
By
–
Hey, for baby AGI I dropped the code into GPT4 and asked it to write a research paper. It’s a little bland, but works!
-
Microsoft Research HuggingGPT Codebase Exploration
By
–
current status Trying out @microsoft research's cool HuggingGPT codebase
-
Integrate with Hugging Face Models Hub
By
–
Very cool! You should integrate with http://
hf.co/models (cf https://
github.com/huggingface/hu
ggingface_hub
…) -
Master Data Science Interview Skills: Six Proven Strategies
By
–
Explore 6 Sure Ways to Ace Your Data Science Interview https://
catherinescareercorner.com/2021/09/22/exp
lore-6-sure-ways-to-ace-your-data-science-interview/
… #DataScience #dataScientist #DataAnalytics #BigData #certification #Coding #100DaysOfCode #CodeNewbie #technology #tech #Python #Azure #SQL #data #WomenInTech -
AI Roles: LLM Development, Prompt Engineering, and RLHF Orchestration
By
–
Most PE jobs in 2023 are probably just LLM-adjacent app development. My job is more developing prompt corpora, writing evaluations, and orchestrating the human work that goes into RLHF. Anthro's PE role is probably similar to mine but not many others like it.
-
Learning to Code Unlocks Exciting AI Use Cases
By
–
if i new how to code i feel like the use cases would be more exciting at the moment
-
Running Baby AGI on Replit: Helpful Setup Tips
By
–
Helpful tip if you want to run baby AGI in Replit
-
Self-Healing Concept in LLMs Beyond Code Generation
By
–
it's crazy because the self-healing concept generalizes beyond just code gen, LLMs are actually pretty good at recognizing errors in most types of outputs and will fix them automatically if you prompt them correctly check out "RCI prompting" in this: https://
arxiv.org/pdf/2303.17491
.pdf
…