19. second year undergrad. i read papers and build things. that's it.
build, train, and compare ml models through a ui. no code required.
plans queries, searches the web, and synthesizes reports using langgraph + ollama.
detects vehicles, pedestrians, and road hazards with severity-based alerts via yolov8.
fine-tuned resnet18 on cifar-10 using imagenet weights after reading the resnet paper.
applied yolov8 to road safety after working through the original yolo paper.
from-scratch pytorch implementation of the architecture that started the deep learning era.
implemented residual connections from scratch; trained on standard benchmarks.
full from-scratch implementation of single-shot object detection in pytorch.
a breakdown of how ai agent logic works and how to build it — reposted by the founder of langchain.