The AI world is getting ‘loopy’ AI loops represent a significant advancement where agents prompt other agents to write code, marking a step as large as the transition from manual source code to AI-generated code. These loops allow a swarm of agents to work continuously in the background, endlessly improving tasks like code architecture or abstraction unification. While conceptually similar to recursive loops in computer science, AI loops employ non-deterministic logic and can be deceptively simple, such as the ‘Ralph Loop’ for goal checking. This approach requires significant computational resources and token expenditure, making it potentially expensive but offering staggering benefits for specific problems.

• AI agents are now prompting other agents to write code, a development termed ‘loops’.
• Loops allow a swarm of agents to work continuously in the background without explicit human intervention for each step.
• This enables continuous improvement of code architecture and unification of duplicated abstractions.
• AI loops are conceptually similar to recursive loops but use non-deterministic logic.
• The ‘Ralph Loop’ is an example that checks if the model has accomplished its goal.
• Agentic loops can be seen as a form of test-time compute, where problems are solved by continuously applying resources.
• AI loops consume tokens rapidly, making them potentially expensive but offering significant benefits.
• The continuous nature of loops means there’s no inherent ceiling on token expenditure. Continue reading https://techcrunch.com/2026/06/22/the-ai-world-is-getting-loopy/