IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
24 articles
21 Sep 2026 · 6 min read
agents
GitHub let Copilot rewrite its own runtime from TypeScript to Rust: 832K lines, 128 PRs, 135 releases, one human in the loop. The regression taxonomy and the incident where two agent sessions overruled each other are worth more than the headline number.
Read more10 Sep 2026 · 5 min read
agentic coding
OpenAI says an internal model coordinated 10,000 agents for 88 hours to solve the Navier-Stokes Millennium Prize problem — then a mathematician accused it of building on unpublished work it had access to. A technical lead's take on the swarm-scale mechanics and the attribution problem every AI-assisted team will eventually hit.
Read more07 Sep 2026 · 5 min read
ai
NVIDIA and Hugging Face published Open-SWE-Traces, SWE-Zero, and SWE-Hero — half a million open agent trajectories with tool calls, patches, and failure cases. A Tech Lead's guide to reusing this format for internal agent evals, not just model fine-tuning.
Read more01 Sep 2026 · 5 min read
ai-agents
Claude Sonnet 5's introductory pricing and GitHub Copilot Studio's promotional credits both expired on the same day. Here's the real math on what changed, why it happened simultaneously, and how to budget for the next one.
Read more28 Aug 2026 · 4 min read
ai
If your team's model pipeline touches the Hugging Face Hub, Inference Endpoints, or Transformers, a hardware company owning your model registry changes the risk calculus. A practical audit for what to check before this deal closes.
Read more22 Aug 2026 · 6 min read
agentic coding
Rachel Laycock's framing from martinfowler.com reduces the whole agentic-software governance problem to one sentence: organisations don't run on code, they run on trust. Here's how to turn that into five concrete guardrails, and why my own overnight-task workflow is a working example of the pattern.
Read more19 Aug 2026 · 5 min read
agentic coding
Remote Control lets you steer a Claude Code session from your phone while it runs on your laptop. I looked past the demo and into the sync-layer design — session state as the source of truth, local execution as a hard boundary — and what it means for building similar tools.
Read more18 Aug 2026 · 5 min read
agentic coding
Cursor's CVSS 9.8 RCE, AWS Kiro rewriting its own MCP config, a wiped Supabase production database, a private-repo leak via GitHub Agentic Workflows — August 2026's incident roundup, distilled into what to actually change in your team's agent permissions.
Read more13 Aug 2026 · 4 min read
ai
A Peking University study found coding agents ignore open-source contribution guidelines even with reminders. Here's a governance framework that relies on gates, not policy text, for engineering teams accepting AI-generated contributions.
Read more
