Jul 13
Another take on the many ways to use AI. I appreciate the autonomy framing over others I've seen.
Levels of Autonomy for AI Agents: operator, collaborator, consultant, approver, and observer.
seen from Singapore
seen from Iraq
seen from United States
seen from United States
seen from Finland
seen from United States
seen from United States
seen from Australia
seen from United States
seen from United Kingdom
seen from United States
seen from United States
seen from United States
seen from United States
seen from United States
seen from United States
seen from United Kingdom
seen from United States
seen from United States
seen from United States
Another take on the many ways to use AI. I appreciate the autonomy framing over others I've seen.
Levels of Autonomy for AI Agents: operator, collaborator, consultant, approver, and observer.
From micro-manager to macro-manager: coding's asynchronous future
Another entry into our collective attempt to understand what AI is doing to software development.
"think of “conductor” versus “orchestrator” as two ends of a spectrum of AI-assisted development, with many hybrid workflows in between."
Tantang OpenAI, Meta Rilis Model AI Muse Spark 1.1
SEANTERONEWS.com – Meta secara resmi meluncurkan sistem kecerdasan buatan (AI) terbarunya, Muse Spark 1.1, pada Kamis (9/7/2026) waktu setempat. Model AI multimodal yang dirancang khusus untuk pemrograman otonom (agentic coding) ini diproyeksikan untuk bersaing ketat dengan berbagai produk serupa yang sebelumnya telah ditawarkan oleh OpenAI dan Anthropic. Muse Spark 1.1 merupakan versi lanjutan…
Self-Scaffolding LLMs: How Ornith-1.0 Rewrites Its Own Harness Mid-Training
A technical breakdown of DeepReinforce’s self-improving agentic coding models There’s a quiet assumption baked into most RL post-training pipelines for coding agents: a human designs the harness, and the model just gets better at using it. The scaffold — memory management, error handling, tool orchestration, retry logic — stays fixed. The policy is the only thing that’s allowed to…
View On WordPress
Agentic UI Development with Claude Code for High Motion Web Design
A technical breakdown of how CLI-based AI agents like Claude Code are moving beyond static component generation to orchestrate complex, production-ready animations and design systems.
Read the full article
Peter Naur's 1985 theory of programming explains why experience matters more in the age of AI-generated code
Orgs serious about software quality must invest in:
Documentation that captures intent
Knowledge sharing practices that transfer mental models
Code review processes that evaluate theoretical consistency
Mentorship programs that develop theory-building skills
A long-form article entitled: "Patterns for Reducing Friction in AI-Assisted Development"
I appreciated the set of patterns (very on brand for thoughtworks): • Knowledge Priming • Design-First Collaboration • Context Anchoring • Encoding Team Standards • Feedback Flywheel