IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
155 articles
25 Aug 2026 · 5 min read
ai
Anthropic logged its 166th outage of 2026 this week, the sixth in August alone. If your product has an LLM call on the critical path, here's the resilience architecture that actually survives that.
Read more21 Aug 2026 · 5 min read
ai-security
OpenAI's new Private Safety Processing architecture claims to catch cross-session attacks like Best-of-N jailbreaking under Zero Data Retention. A look at the actual engineering problem it's solving and whether the design holds up.
Read more20 Aug 2026 · 5 min read
ai-agents
Multi-agent AI systems waste tokens in two specific, fixable ways. A technical breakdown of phase-scheduled activation, context pruning thresholds, and the patterns I actually use to keep a fleet of subagents cheap.
Read more19 Aug 2026 · 6 min read
algorithms
I hosted and reviewed EinkChess, an open-source chess app built for Kindle e-readers. A look at how you write a minimax engine, an offline puzzle trainer, and a client-side app for a screen that punishes every repaint.
Read more19 Aug 2026 · 4 min read
architecture
Daily English practice for tech professionals. Morning session covering invalidate, cache hit/miss, TTL, eviction policy, and edge node with pronunciation guide, exercises, and real-world examples.
Read more19 Aug 2026 · 5 min read
agentic coding
OpenAI's GPT-5.6 Sol Ultrafast, powered by Cerebras' Wafer-Scale Engine, hits 750 output tokens/second — 14x standard inference. I dug into why on-chip SRAM beats HBM for this, and what it means for how we design latency-sensitive agent products.
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 more19 Aug 2026 · 5 min read
agentic coding
If your team uses Claude Code for one task, Cursor for another, and Codex for a third, none of them know what the others just learned. I dug into Memmy and the cross-agent memory layer pattern, and what it actually takes to fix this in production.
Read more17 Aug 2026 · 5 min read
ai
Stripe's reported $7B+ acquisition of OpenRouter — up from a $1.3B valuation three months ago — validates the model-gateway architecture. A Technical Lead's take on when to buy a gateway, when to build one, and what this deal signals for API-routing infrastructure.
Read more
