Autonomous Research Loop Simulator

Overview of the Autoresearch philosophy, the fixed-time budget constraint, and the core evaluation metrics. Autonomous Research Loop Simulator turns that idea into something you can manipulate directly and watch respond.

Overview of the Autoresearch philosophy, the fixed-time budget constraint, and the core evaluation metrics. It focuses on Autonomous AI Agents, Fixed Time Budget Training, Validation Bits Per Byte (val_bpb), Agent-led Code Iteration from the “Introduction to Autonomous Research Frameworks” section.

The “Simulation Speed” slider change the key inputs; the “Start Research Loop” button run actions or reset the demo. Every change updates the visualization in real time, so you can see exactly how each variable affects the outcome.

Autoresearch is an experimental framework developed by Andrej Karpathy that enables AI agents to autonomously conduct LLM research by iteratively modifying training code. The system utilizes a fixed five-minute training… This demo is the interactive piece for the “Introduction to Autonomous Research Frameworks” section. Open the full Autoresearch: Autonomous AI Research Framework course wiki at https://www.getlykke.com/explore/public/autoresearch-autonomous-ai-research-framework-41216b8f-5a7e-4e9e-bb27-4c25e8cb3bb3 for notes, flashcards, quizzes and the other demos.

You'll build intuition for Autonomous AI Agents, Fixed Time Budget Training, Validation Bits Per Byte (val_bpb), Agent-led Code Iteration — and, crucially, see how they behave when you change the inputs, which is hard to get from a textbook or lecture on Autoresearch: Autonomous AI Research Framework alone.