How do AI software engineering agents work? No better place to start than "at the source:" the state-of-the-art open source AI coding agent: SWE-bench has quietly become the industry standard AI coding agent benchmark. The team behind SWE-bench built SWE-agent (at release, state-of-the-art open source AI agent) and with Ofir Press (a member of the team building SWE-bench and SWE-agent), we dive deep on how it works: Read the deepdive here: https://lnkd.in/e3Ha39Rz
The Pragmatic Engineer’s Post
More Relevant Posts
-
Our CEO, A. Kirimgeray Kirimli, dives deep into how AI is reshaping software engineering in his latest article on HackerNoon. From AI copilots that code and debug to the evolving roles of engineers in managing AI tools—discover how AI is revolutionizing the way we work, the skills needed, and the challenges ahead. Curious about the future of engineering with AI? Check out the full article to learn more! https://lnkd.in/dr28h-zX
To view or add a comment, sign in
-
-
Tired of flashy LLM demos that fall apart in production? 😩 Frustrated by non-deterministic AI that’s impossible to debug? 🤯 Join our free Lightning Class next week to learn how to: 🚨 Escape "demo hell" and build scalable, reliable apps 🛠️ Log, monitor, and evaluate AI systems effectively 🎯 Rapidly iterate with prompt engineering and fine-tuning 📦 Use embeddings, vector stores, and structured outputs We’ll dive into: 🔍 First-principles thinking for building robust LLM apps ⚙️ The core building blocks—tracing, testing, evaluation, and iteration 📊 How to tune vendor APIs (temperature, top-p) for real-world results If you want to build real, production-grade AI, this class is for you. Teaching with Stefan Krawczyk on Maven. Sign up here: 🔗 https://lnkd.in/g9nkZ5ur
To view or add a comment, sign in
-
Join a panel of Topcoder Ambassadors - Robinson Muiru, Abiodun Adefusi, Aditya Singh and Yerzhan Utkelbayev for a fireside chat to discuss the Impact of AI on Software Developers! We’ll discuss AI dev tools, future trends, and how to work smarter with AI. Check the link in the comments to register and learn from our industry leaders how to take your AI usage to the next level.
To view or add a comment, sign in
-
-
Excited to share my latest blog post, which serves as a comprehensive guide on running LLMs locally using Llama.cpp. This resource is designed for anyone interested in implementing large language models on any hardware configuration from scratch. Whether you're a seasoned developer or just starting your journey in AI, this guide will equip you with the practical knowledge and steps needed to get your models up and running. Dive into the details and enhance your understanding of local LLM deployment by checking out the full post here: https://ift.tt/0MylkmR.
To view or add a comment, sign in
-
Introducing Applied AI: The Future of Software Engineers and Industries We’re Watching in 2025 In the first issue of our new Applied AI newsletter, Jon Victor looks at two industries AI will impact in 2025. Plus, what’s next for coding automation. Read more 👇
To view or add a comment, sign in
-
🕵 Robot Holmes is back 🕵 Last year I gave the talk "Robot Holmes and the Vision-Language Murder Mysteries" at PyData London and EuroPython. 📖 It is an introduction Vision-Language Models and related tasks, suitable for every skill level, with more of a prosaic than academic approach ;) 🤯 In my head, the story was a lot bigger than what I could fit on the slides. Finally I found the time to write some of it down and aim to publish the whole story until Christmas. 💫 Here is the first part, in my first ever blogpost, on my new shiny blog: https://lnkd.in/d_SKSpBT
To view or add a comment, sign in
-
Ever thought about AI as your coding companion? Dive into the future where your backend dev tasks are automated, optimized, and secured by AI. 🚀 Let's explore this new frontier together!
To view or add a comment, sign in
-
-
AI isn't the future, it’s the present. 🚀 Yesterday, I had the pleasure of attending an incredibly inspiring lecture arranged by CTO Craft. The lecture was led by Johan Sanneblad from RI.SE with the topic "Beyond Code: Navigating the AI-Driven Future of Software Development." Absolutely thrilling, exciting, and full of insights. Mind-blowing and perfectly timed with the release of OpenAI's new GPT-4o. That AI will transform software development is something no one doubts. But it will likely happen faster than anyone could have imagined. Spine-chilling. Understanding these changes is crucial for staying ahead and leveraging technology to our advantage. Now, we're accelerating our AI initiatives even further at Factoringgruppen. Thanks to Humblebee who hosted and Adam Horner who fixed this! 🚀 Onward and upward!
To view or add a comment, sign in
-
-
Sunholo aims to be a post-GenAI company, including using as many GenAI assistants as possible to run the company. The most competitive and relevant at the moment are code assistants. We have just got access to GitHub's Copilot Workspace, ( https://lnkd.in/dPn2MRpy ) which looks to offer massive advantages over others in the space with its integrated UI and massive code based datasets using GPT-4. Here is a screenshot of it implementing the nice-to-have-but-never-prioritised unit tests for the sunholo pip library. ( https://lnkd.in/dUt8eeY9 )
To view or add a comment, sign in
-
-
Deploy a private Llama 3.2 RAG API in just 30 lines of code! Here's what you'll need - LlamaIndex for orchestration - Qdrant for self-hosting a vector DB - Lightning AI's LitServe⚡️ for deployment I have published this work as a Studio, It reads like a blog encapsulating all my code & environment! Link to the studio: https://lnkd.in/gXp3ey_e ___ Find me → https://lnkd.in/em_V4unu ✔️ Everyday, I share insights and tutorials around AI and Machine learning!
To view or add a comment, sign in
-