4Latent Space (swyx)·
AIEWF Daily Dispatch: Loops debate and state of AI engineering at AI Engineer World's Fair
The AI Engineer World's Fair concluded with a debate about loops in agentic systems, a report on the state of AI engineering, and closing keynotes on what to build next. The dispatch from Latent Space covers the final day of the conference, summarizing key themes and discussions. The loops debate likely concerns architectural patterns in agent design, a topic of active interest in the practitioner community.
Related guides (3)
Related events (8)
AIEWF Daily Dispatch: Agent loops, software factories, and open models dominate AI Engineer World's Fair
A dispatch from the AI Engineer World's Fair (AIEWF) reports that Tuesday's sessions centered on agent loops, agent engineering patterns, and the concept of 'software factories' as an emerging paradigm. Open models were also a prominent topic of discussion. The piece reflects practitioner-level discourse at a major AI engineering conference.
AIEWF Daily Dispatch: Autoresearch and the tension between AI and human agency
A conference dispatch from AI Engineer World's Fair 2026 covers debate between proponents of fully automated 'software factory' and 'autoresearch' visions versus speakers defending human understanding and control. The piece captures live tension at a major practitioner conference around how much autonomy AI systems should have in research and software development workflows. The framing surfaces a recurring fault line in the agent-tool ecosystem between automation maximalism and human-in-the-loop approaches.
AINews: Loopcraft — the art of stacking loops in AI systems
Latent Space's AI News digest highlights a concept called 'Loopcraft' — the art of stacking loops in AI agent or system design — attributed to Peter Steinberger, Boris Cherny, and Andrej Karpathy. The piece appears to be a quiet-day editorial spotlight on a conceptual framework rather than a major release or paper. The framing suggests this is a design pattern or mental model relevant to agentic AI architectures.
Andrew Ng outlines three-loop framework for agentic software development
Andrew Ng describes a 'loop engineering' framework for building software with AI coding agents, comprising an agentic coding loop (agent writes/tests/iterates autonomously), a developer feedback loop (human steers at higher product level), and an external feedback loop (user testing, A/B). The piece contextualizes the buzzphrase popularized by Claude Code creator Boris Cherny and OpenClaw creator Peter Steinberger. Ng argues humans retain a 'context advantage' over AI systems that justifies continued human-in-the-loop involvement in product decisions.
Open Questions About the Future of Software Engineering
Andrew Ng offers a contrarian view against AI-driven mass unemployment forecasts, citing rising software engineering job postings from a Citadel Securities report as evidence that AI may expand rather than contract the profession. He outlines five emerging trends in software engineering—including the product management bottleneck, higher-level code interaction, and reduced technical debt costs—alongside open questions about team structure, curriculum, competitive advantage, and agent-driven workflows. The commentary frames these themes around DeepLearning.AI's upcoming AI Developer Conference on April 28-29 in San Francisco.
The Batch Issue 359: Loop Engineering for Agentic Coding, GLM-5.2 Open-Weights Release, Apple On-Device Models
Andrew Ng's weekly letter introduces a framework of three nested loops for agentic software development (engineering loop, developer feedback loop, external feedback loop), contextualizing the 'loop engineering' trend popularized by Claude Code and OpenClaw creators. The issue also covers Z.ai's GLM-5.2, a 753B MoE open-weights model with 1M token context that claims first place among open models on Artificial Analysis Intelligence Index v4.1 and leads all models on PostTrainBench for long-running agentic tasks. Additional coverage includes Apple's recipe for on-device models and AI education trends.
Zvi Mowshowitz AI weekly roundup #173: AI Pauses
Zvi Mowshowitz's weekly AI digest issue #173 covers recent developments in the AI landscape, with a focus on AI pauses as a central theme. The post is a curated commentary roundup from a well-followed analyst tracking frontier AI developments. The body provided is too sparse to extract specific claims, but the title signals coverage of AI pause proposals or policy discussions.
Zvi Mowshowitz AI weekly roundup #172: The First Fable
Zvi Mowshowitz publishes his 172nd weekly AI roundup covering developments in the AI/ML landscape. The post references a visit to Lighthaven and covers a week described as eventful. As a recurring high-signal commentary digest from a respected AI analyst, it likely synthesizes multiple frontier developments, safety research, and industry moves.