IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
279 articles
07 Sep 2026 · 5 min read
ai
Nemotron 3 Ultra pairs Mamba state-space layers with transformer attention and a mixture-of-experts router to hit a 1M-token context at 5x the inference throughput of comparable dense models. A Tech Lead's read on the architecture and where it changes agent deployment math.
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 more04 Sep 2026 · 5 min read
agentic coding
OpenCode, the open-source terminal coding agent, grew past 170,000 GitHub stars by staying model-agnostic and monetizing through Zen, a zero-markup inference gateway. A Tech Lead's breakdown of the bring-your-own-model economics and when it actually beats a single-vendor coding agent subscription.
Read more04 Sep 2026 · 4 min read
agents
Console went from a $6.2M seed to a $500M acquisition by Palo Alto Networks in about two years, automating IT help desk tickets with AI agents. A Tech Lead's breakdown of what made an agentic ITSM layer worth that price, and how to evaluate whether your own ticket queue is a good target for the same pattern.
Read more04 Sep 2026 · 5 min read
agents
OpenAI's GPT-6 Astra ships with a 1M-token context window and browser/computer control that works by reading pixels, not APIs. A Tech Lead's take on what this actually unlocks, where it breaks, and how to design review gates before you let it touch production systems.
Read more03 Sep 2026 · 5 min read
agentic coding
McKinsey's State of AI 2026 survey found a third of organizations skipped a software purchase because agentic coding could build it in-house — but the share reporting real EBIT impact from AI didn't move. What that gap actually means for a build-vs-buy call, from someone who's made a few of them this year.
Read more03 Sep 2026 · 5 min read
ai
Google split Gemini 3.8 Flash into a general workhorse and a gated Cyber variant that finds vulnerabilities and writes patches autonomously. A Tech Lead's take on what changes when the same model does discovery and remediation — and why the patch review step just became your real bottleneck.
Read more02 Sep 2026 · 5 min read
ai
Anthropic didn't touch Fable 5.1's per-token price — it cut cache-read cost by 75%. That's not a discount, it's a signal about which architecture pattern the platform now rewards. Here's how I re-cut my prompt structure around it.
Read more02 Sep 2026 · 5 min read
agentic coding
Coder's new Agent Relay lets Cursor's cloud agents execute inside a customer's own network, with SpaceXAI as launch partner. A look at what this self-hosted execution pattern actually solves, and what it doesn't.
Read more
