When I got back to MIT, I was eager to keep working in edtech. I found the prof in charge of @MITAppInventor and knocked on his door to ask how I could help. To my surprise, Hal invited me to be a research assistant in his lab through the @UROP_mit program! (5/7)
CODE
-
Teaching Computer Science with MIT App Inventor in Barcelona
By
–
One of my favorite memories in undergrad was teaching at a high school in Barcelona through @MISTIatMIT Global Teaching Labs! As a new teacher, I wanted to empower my students in computer science in my one month there. That’s when I stumbled upon @MITAppInventor
. (3/7) -
Developer Returns to Open-Source Coding Roots
By
–
In part but I’m mostly going back to my open-source coding roots
-
Improved Documentation for Custom LangChain Agents
By
–
Better documentation for understanding how custom agents work @samcwl added some much needed comments in both the documentation and the below notebook on the expected LLM output to get it to work with custom agents https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/custom_agent.html
… -
v0.0.65 Release: Documentation Fixes and AI Model Support
By
–
v0.0.65 Doc Fixes – Francis, Chetanya Rastogi
Prompt improvements – @fpingham @brunotorious Support for @AI21Labs experimental models – xettrisomeman
Fix default @CohereAI embedding model – Sasmitha Manathunga Some doc improvements, listed -
FAISS Vectorstore Saving and Loading Guide
By
–
Instructions for saving and loading FAISS vectorstore You just want to create your vectorstore once, and then pass it around. We added some easy documentation on how to do so. https://
langchain.readthedocs.io/en/latest/modu
les/utils/combine_docs_examples/vectorstores.html#saving-and-loading
… -
GroqFlow Proof Points: Computer Vision and NLP Models
By
–
Check out GroqFlow proof points with any of these models:
Computer Vision: DeiT-tiny, GoogleNet, MobileNetV2, ResNet50, SqueezeNet, Yolo v6
Natural Language Processing: Bert Tiny, Bert Base, DistilBERT, ELECTRA, MiniLM v2, RoBERTa, Speech Processing, M5 -
GroqFlow GitHub Discussions Open for Model Requests
By
–
Connect at http://
github.com/groq/groqflow/
discussions
… to request additional models or proof points -
YOLO Object Detection for Underwater Trash Detection
By
–
Learn how YOLO object detection can help create a greener environment. If you haven’t already, check out our blog post, which trains YOLOv6 on underwater trash detection dataset. https://
learnopencv.com/yolov6-custom-
dataset-training/
… #yolov5 #yolov6 #yolov7 #objectdetection #trashdetection #ai -
Training Data Copying vs Generalization in AI Models
By
–
Y podría ser un detalle sin mas, si esta no fuera la clave que diferencia entre una IA que copia y otra que generaliza a nuevas imágenes. Sobre esa interpretación errónea que hacen, luego construyen frases como estas que son incorrectas. No, no se copia el "training data".