/AI

Onboarding To A ‘Legacy' Codebase With The Help Of AI

- Birgitta Böckeler tl;dr: “To get an idea for how well this works and what the potential is, I picked an issue of the open source project Bahmni and tried to understand the issue and what needs to be done with the help of AI. Bahmni is built on top of OpenMRS, which has been around for a very long time. OpenMRS and Bahmni are good examples of very large codebases with a lot of tech debt, representing a lot of different styles and technologies over time.” Birgitta shares her observations about what AI could and could not help with in such a use case.

featured in #542


How Developers Really Use AI

tl;dr: How much are programmers really using AI? How useful is it actually? We wanted to know for sure. We surveyed software developers to uncover the real impact of LLMs like ChatGPT on their work. From debugging to project planning, the responses revealed surprising strengths and notable gaps. Check out our findings to see where AI shines and where it still falls short.

featured in #542


Objective Evaluations For AI Systems

- Kelly Moon tl;dr: AI systems are only as good as the benchmarks and evaluations they are measured against. Learn how to evaluate AI systems.

featured in #540


Bringing AI-Powered Answers And Summaries To File Previews On The Web

tl;dr: From the team at Dropbox: "Both our summarization and Q&A features LLMs to find, compare, and consolidate the content of the file. An LLM works by ingesting content as text, transforming the ideas contained within it into a numerical representation, and comparing those numerical representations against both the input query and an internal corpus of knowledge to answer the question. This effectively enables a computer to consume and compare information semantically, rather than lexically.”

featured in #532


Why Build When You Can Deploy Speech AI Instantly

- Kelsey Foster tl;dr: Not sure whether to build or buy an AI speech recognition system? Our comprehensive guide breaks down the key considerations, from accuracy and internal resources to speed of iteration and data security. 

featured in #531


Leveraging AI For Efficient Incident Response

tl;dr: From the team at Meta, “We’re leveraging AI to advance our investigation tools even further. We’ve streamlined our investigations through a combination of heuristic-based retrieval and large language model (LLM)-based ranking to provide AI-assisted root cause analysis. During backtesting, this system has achieved promising results: 42% accuracy in identifying root causes for investigations at their creation time related to our web monorepo.”

featured in #526


How Developers Really Use AI

tl;dr: How much are programmers really using AI? How useful is it actually? We wanted to know for sure. We surveyed software developers to uncover the real impact of LLMs like ChatGPT on their work. From debugging to project planning, the responses revealed surprising strengths and notable gaps. Check out our findings to see where AI shines and where it still falls short.

featured in #521


How Does AI Impact My Job As A Programmer?

- Chelsea Troy tl;dr: “It’s how human programmers, increasingly, add value. Figure out why the code we already have isn’t doing the thing, or is doing the weird thing, and how to bring the code more into line with the things we want it to do. Chelsea argues that this “conveniently comprises most of the job these days: read code. Analyze it. Understand it. Repair it.”

featured in #519


How Does ChatGPT Work? As Explained By The ChatGPT Team

- Gergely Orosz tl;dr: When you ask ChatGPT a question, several steps happen: (1) Input: We take your text from the text input. (2) Tokenization: We chunk it into tokens. A token roughly maps to a couple of unicode characters. You can think of it as a word. (3) Create embeddings: We turn each token into a vector of numbers. These are called embeddings. (4) Multiply embeddings by model weights: We then multiply these embeddings by hundreds of billions of model weights. (5) Sample a prediction. 

featured in #508


I Accidentally Built A Meme Search Engine

- Harper Reed tl;dr: “I built a meme search engine using siglip / CLIP and vector encoding images. It was fun and I learned a lot. I have been building a lot of applied AI tools for a while. One of the components that always seemed the most magical has always been vector embeddings. Word2Vec and the like have straight blown my mind. It is like magic.” Harper describes his journey and shares the results. 

featured in #508