Ayush MangalFluid/SelfSummoning my best impression of Po from Kung-fu-panda…who am I?3 min read·Apr 7, 2024----
Ayush MangalSmart enough?Oh you are very smart, it must be easy for you, right? yeah smartass, it ain’t4 min read·Apr 7, 2024----
Ayush MangalFLARE — “Advanced” RAG implemented from scratchIn an effort to learn more about LLMs, it was inevitable that I’d come across RAG (or Retrieval Augmented Generation). After watching a…8 min read·Nov 16, 2023--1--1
Ayush MangalA hacky minimal Tree of Thoughts implementationDoesn’t work at all, but good enough to understand7 min read·Nov 8, 2023----
Ayush MangalinGoPenAICreating an AMA bot for my personal website using LLMsYes, I am doing an LLM post after cringing about the gazillions of the already existing ones, but it's my blog, so fuck it.7 min read·Aug 22, 2023----
Ayush MangalOn being aloneNo, this is not a post about introverts or how introverts are some sort of a special species with zen-like superpowers to somehow led the…4 min read·Jun 3, 2023----
Ayush MangalRL with diffusion — IDiffuser: Reinforcement Learning with Diffusion Models14 min read·May 29, 2023--2--2
Ayush MangalConsuming Vs CreatingA blank piece of paper is God’s way of telling us how hard it is to be God. — Sidney Sheldon5 min read·Jan 19, 2023--1--1