Why behavior outlives implementations
Sprites - Stateful sandboxes
Persistent, hardware-isolated execution environments for arbitrary code. Run AI agents, untrusted code, and more in secure sandbox environments with checkpoint & restore.
The New Software Lifecycle
I co-wrote a Google whitepaper about how AI is changing the software lifecycle. I'm not going to summarize the whole thing. Instead, here are the handful of ...
Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study
As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.
Tests Are The New Moat | Daniel Saewitz
As AI becomes better at cloning people's open source work, what ends up becoming most valuable are software contracts, tests, and API surface area. This clashes the incentives of clearly defining your commercialized open source software with protecting it.
Gas Town’s Agent Patterns, Design Bottlenecks, and Vibecoding at Scale
On agent orchestration patterns, why design and critical thinking are the new bottlenecks, and whether we should let go of looking at code
Software Acceleration and Desynchronization
A look at the ever-present drive to make software delivery faster and how it might break down various activity loops in organizations.
Live code with Tidal Cycles | Tidal Cycles
Live coding environment for making algorithmic patterns
Pony
An open-source, object-oriented, actor-model, capabilities-secure, high-performance programming language.
What Functional Programmers Get Wrong About Systems - Ian Duncan
Type systems verify properties of programs. Production correctness is a property of systems. The gap between these is where the interesting failures live.
AI Tools Accelerates Coding, but Not Overall Software Delivery, GitLab Research Finds
GitLab's 2026 AI Accountability Report highlights an AI Paradox: although 78% of developers say they code faster, overall software delivery has not accelerated due to downstream testing and review bottlenecks and new challenges for enterprise governance and traceability.
Vibe Maintainer
Some attendees at an AI Tinkerers meetup in early Feb were asking me what it’s like to be the maintainer of a big OSS project where the…
Opinion | The A.I. Disruption Has Arrived, and It Sure Is Fun
We’re entering a new renaissance of software development. We should all be excited, despite the uncertainties that lie ahead.
Restate - Build innately resilient distributed apps
Restate is a lightweight runtime that lets developers build innately resilient distributed apps without the complexity tax.
Deterministic Core, Non-Deterministic Shell - Outdata
Determinism, architecture, and the de-sloppification of legacy code.
