What’s going on with you, Sirji?
If you are new here, Sirji is an open-source AI software development agent. Internally it works as a combination of planner, coder, researcher, and executor agents. We are building Sirji as a VS
Artificial Intelligence
AI topics spanning across fine-tuning, inference, optimisations, cutting-edge trends, LLMs, breakthroughs, and practical applications.
Sirji Updates - VS Code Extension (launch)
After releasing the dogfood version, we got busy reimagining Sirji as a VS Code extension. This extension brings an interactive chat interface right within your Visual Studio Code IDE. Here’s what the
Sirji Updates - Episode 3 (The first run)
So the end-to-end stitching for the dogfood release is done. And we took Sirji for a spin. The problem statement was: Make a simple website with a server that uses Yahoo API to
Sirji Updates - Episode 2
Sirji’s dogfood release is just around the corner, and we have a whole bunch of updates. InterfaceDogfood is going to be our very first release, and it won’t have a browser-based
Sirji Updates - Episode 1
Yesterday, we told the world about Sirji, an open-source AI software development agent, inspired by Devin. And with that, we got to work. We promised to build in public. And so, here's our
Cross-Pollination is all you need: Transfer learning in AI
In our previous blog, we talked about the theory related to transfer learning. We discussed the recommended method for transfer learning: Freeze the layers with weights from the pretrained model for the first
Co-Maintaining NIAH: A Journey in Open Source and Model Benchmarking
Recently, I took the opportunity to co-maintain an open-source repository called Needle in a Haystack (NIAH). NIAH is a benchmarking technique for Large Language Models (LLMs), where the model is tasked with identifying
An OpenSource Prompt Evaluator for Product Managers
At True Sparrow, we enjoy delving into the user persona, understanding their challenges, and brainstorming solutions to address them. Once a consensus is reached, we often provide low-fidelity demos to clients to gather
How to Train Your D̶r̶a̶g̶o̶n̶ AI Model?
You would think transfer learning is very straightforward and simple. Alas, why not, you just initialize weights from a proven NN which solved a different, but similar enough problem. Simple enough. Right? Yes,
OpenAPI meets OpenAI: AI-Driven Dynamic Mock APIs
In a fast-paced development environment, we often encounter various types of blocking dependencies within or between teams. One such dependency is getting the backend APIs ready to be integrated into consumer interfaces and