ai
I was surprised to find that Github Copilot still doesn't support answering questions over your entire codebase through @workspace /explain command. This feature seems to be part of their roadmap. It got me thinking what the real challenges are behind scaling reasoning across entire codebase given that they
ai > concepts
A very high-level summary of RL. Dall-e's somewhat inaccurate representation of RL state-space RL is an approach to efficiently search state-space of a well-defined system. We can think of the system as a graph with states (vertex) and actions (edges) that lead to change in state. In its
ai
I've been thinking about reasoning abilities in LLMs. To what degree do they exhibit reasoning abilities vs reformulation via statistical patterns? After all, they are increasingly referred to as "reasoning-engines" these days, but do they reason? I also came across an interesting post that solidified some
ai
Transformer architectures have unlocked tremendous potential in the context of Machine Learning problems. It has become the basic building block for learning and generating all modalities: language, vision, speech. But what changed with Transformers? We had kernel methods available for decades. In short, transformers allows for efficient context-aware learning. A
ai
The field of NLP has made tremendous progress in last 10 years. These Deep Learning approaches, from Word2Vec to GPT4, show remarkable capabilities can be achieved through representation learning. Tracing the journey back 5 years shows progress has mostly been to scale and engineer these LLMs on data and compute.
ai
2022 was a remarkable year for the field of Machine Learning AI as years of landmark research ideas culminated into applications with strong PMF. Image generation and dialog systems surpassed most of our expectations, shifting near-term upper-bound on coherence and reasoning abilities of these approaches. Products like Stable Diffusion, Midjourney,
ai
This is an ongoing note around Pytorch and its quirks. PyTorch is a library for Neural Net model building using Python. It provides: a) an array-based programming model, known as Tensors b) an automatic differentiation engine, utilizing the chain-rule of differentiation c) hardware acceleration through cuDNN, parallelization, and graph optimizers