home on meowy

What RAG actually is

Fri, 29 May 2026 00:00:00 +0000

Nowadays LLMs are like superintelligent ai heroes that can understand and help you with everything from writing to coding. But most LLMs are frozen in time, think of like an isekai-ed hero that’s been hit by truck-kun and sent to another world where they’re stuck forever. But that hero doesn’t know anything about the world and still needs to learn and adapt for the survival of the new world they’re sent to. Just like that, LLMs are stuck in frozen time also. It doesn’t know anything about specific company docs, personal notes, or even worse cause when it doesn’t know what it doesn’t know, it doesn’t stay quiet, it just starts to hallucinate and make up things that are not true. We can definitely fine-tune the model to help us with tasks but that’s super slow and expensive to do. And we have to keep doing it every time the data changes.

About

Mon, 01 Jan 0001 00:00:00 +0000

about this blog

this is my corner of the internet. i write about what i build and what i learn along the way, minus the buzzwords.

posts are sorted by category on the home page, or all in one place in the archive
built with hugo. no trackers, no third-party scripts
there is an rss feed if you like getting new posts the old way
the best page here is piku’s

about me

i’m sushmita r, aka meowy. full-stack engineer, 5+ years shipping software: full-stack apps, dev tooling, and on-chain systems. frontend in next.js with typescript; backends depend on the job: rust, go, or python.

meow

Mon, 01 Jan 0001 00:00:00 +0000

Short for Pikachu. Born 27 August 2018. Picky eater, snack maximalist, professional sunbeam follower. Co-author of every late-night refactor, by way of walking across the keyboard.