IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
279 articles
27 Aug 2026 · 6 min read
agentic coding
SpaceXAI's Think Fast 2.0 merges speech recognition, reasoning, and synthesis into a single speech-to-speech model over one WebSocket. I built a customer-support voice agent against it and pulled out the production best practices that actually matter: timing, interruption, resumption, and security.
Read more25 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 more25 Aug 2026 · 5 min read
ai
GLM-5.3 just jumped from 4.6 to 28.3 on Terminal-Bench 3.0 at a fraction of frontier pricing. Here's the routing architecture we actually shipped to stop overpaying for tasks that don't need it.
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
xAI open-sourced Grok Build, a terminal coding agent powered by Grok 4.6 with subagents, plan mode, and worktree support. I tested it side by side with Claude Code on real refactoring work. Here's what actually differs.
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 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 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 more18 Aug 2026 · 5 min read
agentic coding
Wiz's autonomous Red Agent found a real, exploitable CI/CD vulnerability in a Snowflake repo — one that human review plus Copilot Autofix had already passed. A technical lead's take on the AI-versus-AI security shift, and why it changes your review checklist.
Read more
