13 articles by Joas Pambou.
Streaming UIs are an easy concept on the surface, but are quite complicated in practice. There are many considerations that need to be accounted for, from layout shifts and motion preferences to proper markup and various states, that may not be instantly obvious. What happens if the stream is interrupted? Can users tab through the UI on the keyboard as it shifts? What ARIA attributes might be need
Most developers spend their days fixing bugs, shipping features, and jumping into the next sprint without even thinking about it. After a while, you begin to ask yourself, “Is this still what I want to be doing?” This article looks at how you can move into a new direction in your career without starting from scratch, and how the skills you already use, like problem-solving, communication, and empa
Design systems are more than style guides: they’re made up of workflows, tokens, components, and documentation — all the stuff teams rely on to build consistent products. As projects grow, keeping everything in sync gets tricky fast. In this article, we’ll look at how smart tooling, combined with automation where it makes sense, can speed things up, reduce errors, and help your team focus on desig
Animation makes things clearer, especially for designers and front-end developers working on UI, prototypes, or interactive visuals. Manim is a tool that lets you create smooth and dynamic animations, not just for the design field but also in math, coding, and beyond, to explain complex ideas or simply make everything a little bit more interactive.
Shouldn’t there be a way to keep your apps or project data private and improve performance by reducing server latency? This is what on-device AI is designed to solve. It handles AI processing locally, right on your device, without connecting to the internet and sending data to the cloud. In this article, Joas Pambou explains what on-device AI is, why it’s important, the tools to build this type of
In this third part of the series, you are looking at two models that handle all three modalities — text, images or videos, and audio — without needing a second model for text-to-speech or speech recognition.
In the second part of this series, Joas Pambou aims to build a more advanced version of the previous application that performs conversational analyses on images or videos, much like a chatbot assistant. This means you can ask and learn more about your input content.
Joas Pambou built an app that integrates vision language models (VLMs) and text-to-speech (TTS) AI technologies to describe images audibly with speech. This audio description tool can be a big help for people with sight challenges to understand what’s in an image. But how this does it even work? Joas explains how these AI systems work and their potential uses, including how he built the app and wa
Language models have shown impressive capabilities. But that doesn’t mean they’re without faults, as anyone who has witnessed a ChatGPT “hallucination” can attest. In this article, Joas Pambou diagnoses the symptoms that cause hallucinations and explains not only what RAG is but also different approaches for using it to solve language model limitations.
Discuss the concept of large language models (LLMs) and how they are implemented with a set of data to develop an application. Joas compares a collection of no-code and low-code apps designed to help you get a feel for not only how the concept works but also to get a sense of what types of models are available to train AI on different skill sets.
In this article, Joas Pambou builds the tool to provide a sentiment score in **real-time** with enhanced user experience by providing multilingual support. You will use an OpenAI library called Whisper that transcribes audio files into text and detects the language, and Gradio, a UI framework, to establish the interface.
In this article, we’ll explore how to build a chat summarizer using the Cohere API and deploy it as a web application using Gradio.[ Cohere](https://cohere.com/) is an AI platform that provides state-of-the-art natural language processing models for a variety of tasks, including summarization. We’ll cover the steps involved in training the summarizer using sample chat conversations, interacting wi
Dive into an article where you will build an app that evaluates audio files for positive and negative sentiments. The idea is that you will create an interface for uploading an audio file, then transcribe the contents into text before analyzing the text and assigning it a positive or negative score for how the tone is perceived.