Articles from latent.space
6 kept
- Skill engineering and the case against one-shot AI design
Paul Bakaus argues AI agents need “skill engineering” to give designers precise control, rejecting full automation in favor of human judgment steering the final 20% of creative work.
- Autoresearch: The feedback loop behind self-improving agents
Autoresearch uses outer loops with feedback signals and human input to let agents improve and maintain systems, reducing bottlenecks while keeping humans central.
- GitHub's plan for Agents — Kyle Daigle, GitHub
GitHub COO Kyle Daigle discusses how AI agents caused platform activity to surge 1400% in 2026, straining infrastructure and forcing GitHub to rethink open-source social contracts and reliability.
- [AINews] The Two Sides of OpenClaw - Latent.Space
Peter Steinberger's TED talk on OpenClaw contrasts with sober engineering reports detailing 60x more security incidents than curl and rampant malicious contributions.
- How to Kill the Code Review - by Ankit Jain - Latent.Space
Human code review is becoming obsolete at AI-generated code scale; teams should shift to upstream spec review, adversarial agents, and deterministic verification.
- Brex’s AI Hail Mary — With CTO James Reggio - by Allen Park
Brex's CTO describes how a 10-person AI team, agentic coding adoption, and company-wide AI fluency training fueled a turnaround to $500M+ ARR.