Don Syme, GitHub Next, Visiting Professor, King's College London
(This blog post is written in personal tone, but relates to our work at GitHub Next and may be moved to https://githubnext.com in future. A huge thank you to Peli de Halleux, Joe Zhou, Eddie Aftandilian, Russell Horton, Idan Gazit and many others at GitHub Next, and the GitHub platform leadership of Mario Rodriguez. I'm … Continue reading Towards Semi-automatic Agentic Performance Engineering
[ notes made for a panel at AI Native Dev podcast ] LLMs and Coding Agents affect all aspects of software engineering - documentation, specifications, tasks, intent, summaries, code generation, methodology, testing and many more - all are being tumbled about and turned inside out, by the arrival of LLMs on the scene. My usual … Continue reading Intent, meet Toolchain
In previous posts I've written about Natural Language Programming, Dijkstra's Ghost - the End of The Symbolic Supremacy and Ephemeral Editable Specifications (aka Extract, Edit, Apply). These touched on the topics of Natural Language Programming and the role of Specifications in AI-native programming. Today I'd like to step back and address an underlying question: what … Continue reading What Kind of Programming is Natural Language Programming?
Dijkstra's Ghost and the End of The Symbolic Supremacy. I recently found myself arguing with the ghost of Edsger Dijkstra on LinkedIn. This is not a comfortable position for a computer scientist to find themself in. More specifically, I was triggered by this LinkedIn post, which quoted Dijkstra's 1978 paper "On the foolishness of natural … Continue reading On Natural Language Programming
Ever since we started working on "task-oriented programming" (aka vibe coding) in 2023, our group at GitHub Next have been throwing around ideas related to "continuous" tasks in software repositories: Continuous Code Cleanup, or Continuous Documentation and so on. This finally bubbled up as the Continuous AI project, locating it within the tradition of Continuous … Continue reading On Continuous AI for Test Improvement
I'm excited to share our latest research demonstrator from GitHub Next - "GitHub Agentic Workflows - Natural Language Programming for GitHub Actions" .https://githubnext.com/projects/agentic-workflows/Agentic Workflows focuses on expressing repository‑level behaviors in natural language and running them on GitHub. Agentic Workflows is not a product and not even a technical preview; it's a vehicle for exploring the agentic design space, … Continue reading GitHub Agentic Workflows
Sharing a write-up of one of our investigations at GitHub Next: Extract, Edit, Apply. Spec-oriented programming is usually seen as "Spec-first", with a compilation step to turn specs into code: Specs are permanent, and Code is ephemeral. This has many obvious problems, including: The instability of LLM code-generation under otherwise small or unimportant changes to … Continue reading Extract, Edit, Apply – a design pattern for AI
In 2023 we at GitHub Next invented an early form of task-oriented programming in a system called Copilot Workspace. Copilot Workspace was the world's first implementation of human-guided, task-oriented software development. It was the first interactive, structured AI-for-Code experience with the Task --> Specification --> Plan --> Code pathway. It had flaws, which I'll mention … Continue reading Copilot Workspace and the birth of Task-Oriented Programming
Originally published at https://github.com/githubnext/copilot-workspace-user-manual/blob/main/origins.md, April 29, 2024 At GitHub Next we work in phases: ideation, build, ship, learn. Every phase is about learning. In May 2023, after launching Copilot-X, our ideation around the SpecLang project led to new explorations of how to incorporate natural language — and user edits to natural language — into the … Continue reading Origins of Copilot Workspace
The fundamental lesson of the original GitHub Copilot (i.e. completions) is that AI tooling is an endless sequence of divergence and re-convergence between the human and the AI. This is the "Co" in "Copilot".In all AI literature, an agent is fundamentally regarded as autonomous: able to make its own decisions, take its own actions - … Continue reading The Coagent Manifesto
GPT-4 and other LLMs (Large Language Models) are driving a tidal wave of innovation in applied AI. However used without augmentation they have very limited calculational capabilities and make mistakes calculating with numbers. In this project, we describe a simple, general technique to address this, apply it to some widely reported real-world failures of GPT-4-based … Continue reading Augmenting GPT-4 with Calculational Code
@dsyme on software 