ai - Hexmos Journal

Building a Bayesian Spam Classifier from First Principles

We work through the original Bayesian Spam Classifier paper from Microsoft Research. And then make it practical by applying to the Enron spam dataset

From Logic to Linear Algebra: How AI is Rewiring the Computer

For decades, computers were built for logic -- branching decisions, compilers, databases. But AI flipped the script: today's machines are being rebuilt for one thing above all else -- multiplying matrices at massive scale

API

The API Boom: How AI Is Supercharging the Future of Software

Hey everyone, I'm Shailendra. Recently, I was studying more about APIs while diving deeper into APIs and exploring how the space is evolving, I stumbled upon a few really interesting reports—especially the Treblle API Report for 2024. That got me digging further, and I came across even

Super-Convenient Software, or The End of Workflows as We Know Them

AI is transforming enterprise software by turning complex workflows into simple, one-step processes. Let's explore how this new era of super-convenience is changing the way we build and use software.

LiveAPI v0 Devlogs

Imagine real-time, interactive API docs that update directly from your codebase. LiveAPI is an AI-powered solution designed to remove the effort of traditional API documentation.

I Built a Bot To Help You Write Production Code From API Docs in Minutes, Not Days.

Are you tired of working with API docs and taking days to build solutions? Do you wish you had a way to make your work fast and easy and give your team more time to focus on other tasks.

How LangChain and ChatGPT plugins are getting attacked by this bug

Insecure Output Handling on LLMs deals with injecting poisonous data during the training phase. In this article, we will be focusing on real-world scenarios, practical demos, and prevention mechanisms along with examples.

Credits got depleted and can't create AI images anymore? How to run your own image generator for free

How I overcame the challenge of making AI generated images freely and in high quality without any credit depletion

How ML Model Data Poisoning Works in 5 Minutes

Training data poisoning on LLMs deals with injecting poisonous data during the training phase. In this article, we will be focusing on attack scenarios, previous successful attacks, and prevention mechanisms along with good examples.

Training LLMs Taking Too Much Time? Technique you need to know to train it faster

Training and using LLMs can be a hefty task, By using this technique you can acheive more output with less time and performance.

AI/ML Business Use Cases You Cannot Afford To Ignore

Unsure or anxious about your team's AI/ML strategy? Like many business leaders, I too was a bit confused and anxious. Every day I see new developments in AI/ML flowing into my feeds. And such deluge of activity can be overwhelming for business leaders. How a conversation

How we made an AI Attendance System for better Team Performance

Our team at Hexmos had problems with absenteeism. When the team involved aren’t consistent, it leads to chaos in managing projects and lower team performance.

See all