Experimental Research on Long-Running Autonomous Coding Agents
By
samwillis
The bagel they save for the regulars. Don't skim, savour.
Summary
The article discusses experimental research into running autonomous coding agents for extended periods (weeks at a time) to tackle complex software projects that typically take human teams months. The research involves running hundreds of concurrent agents on a single project, coordinating their work, and observing them generate over a million lines of code and trillions of tokens. The article explores the limitations of single agents for complex projects and examines the natural progression to parallel agent systems.
Key quotes
· 5 pulledWe've been experimenting with running coding agents autonomously for weeks at a time.
Our goal is to understand how far we can push the frontier of agentic coding for projects that typically take human teams months to complete.
This post describes what we've learned from running hundreds of concurrent agents on a single project, coordinating their work, and watching them write over a million lines of code and trillions of tokens.
Today's agents work well for focused tasks, but are slow for complex projects.
The natural next step is to run multiple agents in parallel.
You might also wanna read
How I Used Coding Agents to Automate My AI Research Work in Copilot Applied Science
An AI researcher shares their experience using coding agents to automate intellectual work, specifically building agents that automate parts
GitHub·2mo ago
Anthropic's Claude Sonnet 4.5: AI Model Capable of 30-Hour Autonomous Coding
This article discusses Anthropic's new Claude Sonnet 4.5 AI model, which can code autonomously for 30 hours straight, and explores the broad
The Verge·8mo ago
Agen: Autonomous AI Coding Agents for Complete Software Development Tasks
Agen is a platform offering fully autonomous AI coding agents that can take software development tasks from initial prompt to finished code.
Product Hunt·2mo ago
The operational monitoring gap in production multi-agent AI systems
The article discusses the rapid shift of multi-agent AI systems (like CrewAI, AutoGen, LangGraph) from experimental demos to production infr
bit.ly·2d ago
How AI coding agents are reshaping social science research: Opportunities and concerns
This article examines how AI coding agents are transforming social science research by automating core research tasks traditionally performe
share.google·4d ago
AI agents engage in theft, intimidation, and societal collapse in unsupervised simulation experiment
A new experiment by Emergence AI ran five simulated "AI worlds" for over two weeks, each populated with 10 AI agents powered by models like
share.google·2d ago