Bytes Are All You Need: Transformers Operating Directly On File Bytes
This paper investigates the possibility of performing deep learning classification directly on file bytes without the need for decoding files at inference time. The authors demonstrate ByteFormer, a m...
Datadog Creates Scalable Data Ingestion Architecture
Datadog created a dedicated data ingestion architecture with event-driven architecture (EDA) offering exactly-once semantics for their third-generation event store, Husky. The architecture of Husky se...
Implementing Dapr State Management in ASP.NET Core Web APIs
Learn how Daprs State Management API simplifies handling state in distributed architectures, enabling you to store state across a variety of data stores. With the ability to configure the level of dat...
KNet: A New Way to Use Apache Kafka from .NET
KNet offers a new approach for using Apache Kafka from .NET by executing the Java code of the validated Apache Kafka distribution directly, rewriting APIs only. With KNet, users have access to the sam...
KNet: the Apache Kafka .NET suite
KNet is a comprehensive .NET suite for Apache Kafka APIs providing all features: Producer, Consumer, Admin, Streams, Connect, backends (ZooKeeper and Kafka). This project aims to create a set of libra...
Dapr v1.11 Release Highlights and Local Development of Cloud-Native Apps with Dapr and Testcontainers
The Dapr maintainers released version 1.11 of the distributed application runtime, with new features and upgrades for building microservices reliably and quickly. The Configuration building block is n...
GPT Engineer: AI that builds your codebase based on a prompt
GPT Engineer is an AI tool that generates an entire codebase by asking for clarification on what you want it to build. It is flexible and easy to adapt, allowing you to create your own AI steps and ev...
How to crawl a quarter billion webpages in 40 hours
In this article, the author explains how they crawled 250,113,669 webpages in 39 hours and 25 minutes using 20 Amazon EC2 machine instances for just under 580 dollars. They also discuss the challenges...
Sequence diagrams, the only good thing UML brought to software development
Sequence diagrams shine when documenting parts of a system and how they interact, mapping messages and operations. They can even model conditional and divergent flows. UML, which introduced sequence d...
Insights from Stack Overflow Developer Survey 2023
In May 2023, Stack Overflow conducted their annual survey and received responses from over 90,000 developers. This report delves into developer education, learning to code, experience, roles, territor...
Treat your .NET Minimal API Endpoint as the application layer
In this blog post, Tim Deschryver discusses using as few layers as possible to keep your applications structure easy to navigate. He introduces the Request Endpoint Response (REPR) pattern, which work...
⚡zap⚡ - blazingly fast backends in zig
Zap is a microframework for web applications that is intended to become the replacement for REST APIs written using Flask and MongoDB in Python, but in the zig programming language. This super-alpha f...
Developer experience: what is it and why should you care?
This article explores how investing in a better developer experience frees developers to do what matters most: building great software. Developer experience (DevEx) examines how people, processes, and...
Augmenting Language Models with Long-Term Memory
Existing large language models (LLMs) have limitations due to input length limits, preventing them from utilizing rich long-context information. To address this issue, we propose a framework called La...
Function Calling and API Updates by OpenAI - New Steerable API Models, Function Calling, Longer Context, and Lower Prices
OpenAI has announced updates that include new steerable API models, function calling capabilities, longer context, and lower prices. The new function calling capability in the Chat Completions API all...
Harness the power of Large Language Models with Azure Machine Learning prompt flow
Learn how Azure Machine Learning prompt flow can be used to develop innovative applications with human-like text understanding and generation capabilities, transforming industries such as customer ser...
JupyterLab 4.0: A Full-Featured Development Environment with Improved Performance and Accessibility
The Jupyter contributor community has released JupyterLab 4.0, the next major version of their development environment. The new release boasts significant performance improvements, including faster ta...
OpenAI and DeepMind to Give UK Government Access to Their Models
According to an announcement by POLITICO Live, OpenAI and DeepMind will grant the UK government access to their artificial intelligence models. This is part of the UK governments efforts to bolster it...
A New Approach to Computation Reimagines Artificial Intelligence
An in-depth analysis of the limitations of artificial neural networks and the benefits of hyperdimensional computing. By representing information as single hyperdimensional vectors rather than individ...
Chris Lattner: Compilers, LLVM, Swift, TPU, and ML Accelerators | Lex Fridman Podcast #21
Chris Lattner, Senior Director at Google, is one of the top experts in the world on compiler technologies and deeply understands the intricacies of how hardware and software come together to create ef...