IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
166 articles
21 Aug 2026 · 7 min read
agentic engineering
Devin costs $500/mo. Cursor's background agents live in someone else's cloud with your code. So I built the same capability on my own machines, on a Claude subscription I already pay for. Here is the full architecture -- the loop, the data model, the six-phase build, the hardening -- and why 70% of it was infrastructure I already had.
Read more20 Aug 2026 · 4 min read
ai-literacy
Anthropic launched Claude Academy this week to teach delegate-verify-learn as a formal skill. Most engineering orgs gave everyone a seat and no curriculum. Here's a rollout plan that actually closes the gap.
Read more12 Aug 2026 · 4 min read
ai-agents
Anthropic's new self-hosted Claude Code beta lets sessions run on your own infrastructure with internal network access. Here's the rollout playbook — and the compliance gap most teams will miss: prompts still leave your network.
Read more12 Aug 2026 · 4 min read
ai-agents
Innodata's new AI Cyber Training Suite benchmarks coding agents against real CVEs replayed in sealed environments. The best open-weight models fixed 23% of flaws unguided. Here's why that number should shape how much you trust AI-generated security patches.
Read more11 Aug 2026 · 5 min read
ai-agents
Cloudflare's Kitesurf ditches Chromium entirely — Servo's layout engine, Firefox's CSS engine, and a Rust JS engine, running inside Workers V8 isolates. The real benchmarks: 3-7x less resource usage, but Chromium still wins on raw speed.
Read more11 Aug 2026 · 5 min read
agentic coding
Thoughtworks ran a controlled experiment on TDD inside an AI agent loop: red-green cycles cost up to 8.5x more tokens than spec-first prompting, and blind quality judging preferred the non-TDD output. Here's what that means for how you should actually prompt coding agents.
Read more10 Aug 2026 · 5 min read
cloud
PostgreSQL 19 Beta 2 ships parallel autovacuum, in-core online REPACK, and in-core plan advice. Here's what a production-minded technical lead needs to know before touching the beta, with real SQL and config examples.
Read more10 Aug 2026 · 5 min read
aws
AWS EKS engineers published the real root cause of slow CUDA/PyTorch image pulls on Aug 10, 2026: it's serialization, not bandwidth. Two containerd fixes now shipping in EKS Auto Mode — chunked range-request downloads and concurrent layer unpacking.
Read more10 Aug 2026 · 5 min read
ai
Meta released Muse Glimmer on Aug 10, 2026 — an Apache 2.0, 30B agentic LLM that runs on a single consumer GPU with near-zero quality loss when quantized. Here's the real architecture, benchmarks, and when it beats calling an API.
Read more
