Articles for category: AI Tools

March 28, 2025

ikayaniaamirshahzad@gmail.com

Build Full-Stack AI Agents with Custom React Components

Hey everyonešŸ‘‹ I manage our community at CopilotKit, a free and open-source framework for building intelligent companions and, in-app infrastructure.šŸ¤” Think about it like this:šŸ§ CopilotKit allows your agents to take control of your application, communicate what its doing, and generate completely custom UI. Agentic Apps A new wave of Agent-Native apps has emerged – such as Replit’s AI Agent, Vercel’s new v0, and ChatGPT’s Canvas. These apps deeply integrate an AI agent into a native application, allowing for deep human/AI collaboration and human-in-the-loop flows. In this video, we will show you how to add an agent to your app

March 28, 2025

ikayaniaamirshahzad@gmail.com

Fast transformer inference with Metal Performance Shaders Ā· Explosion

We are happy to introduce support for Metal Performance Shaders in Thinc PyTorch layers. This makes it possible to run spaCy transformer-based pipelines on GPU on Apple Silicon Macs and improves inference speed up to 4.7 times. In this post, we will discuss the hardware acceleration facilities of Apple Silicon Macs and how spaCy can use them to accelerate transformer models. We will wrap up the post with benchmarks that show what kind of acceleration you can expect on various Apple Silicon Mac models. Large transformer models are well known to be computationally expensive. This is due to the quadratic

March 28, 2025

ikayaniaamirshahzad@gmail.com

Introducing the LiveCodeBench Leaderboard – Holistic and Contamination-Free Evaluation of Code LLMs

We are excited to introduce the LiveCodeBench leaderboard, based on LiveCodeBench, a new benchmark developed by researchers from UC Berkeley, MIT, and Cornell for measuring LLMsā€™ code generation capabilities. LiveCodeBench collects coding problems over time from various coding contest platforms, annotating problems with their release dates. Annotations are used to evaluate models on problem sets released in different time windows, allowing an ā€œevaluation over timeā€ strategy that helps detect and prevent contamination. In addition to the usual code generation task, LiveCodeBench also assesses self-repair, test output prediction, and code execution, thus providing a more holistic view of coding capabilities required

March 28, 2025

ikayaniaamirshahzad@gmail.com

I’m going back to school

Update: Iā€™ve graduated! You might also be interested in this OMSCS FAQ I wrote after graduation. Or view all OMSCS related writing here: omscs. Iā€™ve been accepted into Georgia Techā€™s Online Master of Science in Computer Science (OMS CS)! Whatā€™s that? Georgia Tech is one of the top schools for computer science (5th on Business Insider and TFE Times, 9th on US News). The price tag? Around USD$7,000. Thatā€™s less than 1/10 of the cost of a degree from comparable US colleges. Furthermore, graduates earn a full Masters degree thatā€™s indistinguishable from those earned by residential students. Bottom line: I

March 28, 2025

ikayaniaamirshahzad@gmail.com

The Tech Stack of a Cloud Computing Startup

At Sliplane.io, weā€™ve put together a tech stack that gets the job done ā€” fast, reliable, and most importantly, easy to maintain and operate. Hereā€™s a quick rundown of what weā€™re working with, from frontend to backend and everything in between. Frontend For the frontend we’re going a bit against the grain of current webdev trends and bet on Nuxt (of course with Typescript and Tailwind) as our framework of choice. This is mostly because Lukas (the co-founder) is a long-term Nuxt.js fan and sponsor! Of course, the frontend is completely hosted on sliplane for proper dogfooding, with Cloudflare as

March 28, 2025

ikayaniaamirshahzad@gmail.com

State of Foundation Model Training Report 2025

Executive summary Lorem ipsum lorem ipsum lorem ipsum About neptune.ai Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry’s standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.

March 28, 2025

ikayaniaamirshahzad@gmail.com

PyData Global 2022: Spancat – Speaker Deck

Named entity recognition models might not be able to handle a wide variety of spans, but Spancat certainly can! Within our open-source library for NLP, spaCy, weā€™ve created a NER model to handle overlapping and arbitrary text spans. Dive into named entity recognition, its limitations, and how weā€™ve solved them with a solution-focused talk and practical applications. Source link

March 28, 2025

ikayaniaamirshahzad@gmail.com

Running Privacy-Preserving Inferences on Hugging Face Endpoints

This is a guest blog post by the Zama team. Zama is an open source cryptography company building state-of-the-art FHE solutions for blockchain and AI. Eighteen months ago, Zama started Concrete ML, a privacy-preserving ML framework with bindings to traditional ML frameworks such as scikit-learn, ONNX, PyTorch, and TensorFlow. To ensure privacy for users’ data, Zama uses Fully Homomorphic Encryption (FHE), a cryptographic tool that allows to make direct computations over encrypted data, without ever knowing the private key. From the start, we wanted to pre-compile some FHE-friendly networks and make them available somewhere on the internet, allowing users to

March 28, 2025

ikayaniaamirshahzad@gmail.com

Image classification API is now live!

After toiling for a few months on this, product image classification is now live on Datagene.io! While the product classification API works with product titles, the image classification API works with product images, though only for fashion. (Github repositiory) Update: API discontinued to save on cloud cost. This is part of a series of posts on building a product classification API: Some facts about the image classification API: Works best with e-commerce like fashion images (as thatā€™s what it was trained on) Top-1 validation accuracy: 0.76; Top-5 validation accuracy: 0.974 Returns results under 300 milliseconds (will be faster in batch

March 28, 2025

ikayaniaamirshahzad@gmail.com

Setting up a translation system for your Android and iOS app

When developing an Android app, managing translations is straightforward: all strings are stored in strings.xml. But when you need to synchronize translations with an iOS counterpart (or even a web or desktop application), things become more complex. Choosing a translation management system We decided to use Weblate, one of the most popular open-source translation management systems. It offers both a hosted version and a self-hosting option. For small-to-medium projects, self-hosting with Docker is a viable choice, providing full control over the translation workflow. Integrating with the Android and iOS apps To streamline the translation update process, we created a script