loops

The article discusses the rise of 'loops' in AI agentic systems, where agents continuously prompt other agents to perform tasks, as a major step beyond simple agent use. Boris Cherny of Claude Code endorses this approach at Meta's @Scale conference.

Andrej Karpathy and Geoffrey Huntley advocate using loops for AI prompts—giving the AI a goal, letting it plan, act, and check its own work—instead of manual single-request interactions.

An article explaining the differences between goal, loop, and schedule commands in AI coding tools like Claude Code and Codex, and providing 15 practical loop examples for running automated tasks.

The article explains the concept of using loops in AI interactions, where the AI iterates on a goal rather than one-off prompts, and discusses the key components of verify, state, and stop conditions.

The tweet discusses the early stage of hierarchy of loops in AI agents, highlighting verification as a key primitive for reliable semi-long-horizon work.

A tweet promoting a resource on engineering loops, described as the current meta.

Boris Cherny and others describe shifting from prompting AI agents to designing autonomous loops that run continuously, using memory files and evaluator patterns for code quality.

A conceptual discussion on the importance of stacking loops in AI agent design, drawing parallels to Sutton's Bitter Lesson and advocating for scalable systems over manual fixes.

Describes a loop command in Cursor to automatically fix flaky tests by running the test suite multiple times, collecting intermittent failures, and fixing or quarantining them until five consecutive green runs.

Peter Steinberger suggests moving from prompting coding agents to designing loops that prompt agents, while @dzhng advises using state machines instead of loops.

The article explains the concept of 'loops' in AI coding, where developers write programs that prompt coding agents instead of manually prompting, as popularized by Peter Steinberger and Boris Cherny, and discusses how this shift represents a new abstraction layer in AI-assisted development.

Boris, the creator of Claude Code, shares a crucial shift: moving from writing prompts to writing loops, letting the model iteratively progress tasks in a repeatable loop instead of providing a one-time answer.

The article argues that AI engineering is evolving from one-shot prompting to building loops that enable models to retrieve context, reason, take action, evaluate, and improve over time, emphasizing that reliable AI systems require designing loops around the model rather than just refining prompts.