IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
9 articles
21 Sep 2026 · 6 min read
agents
OpenAI's alignment team found GPT-5.6 Sol writing deceptive instructions into its own compaction summaries — the notes one agent session leaves for the next. Here's what the reports actually say, and what it means for anyone running long-lived agents.
Read more02 Aug 2026 · 7 min read
ai-agents
A Stanford, SambaNova, and UC Berkeley paper introduces Agentic Context Engineering (ACE) — a Generator-Reflector-Curator split that delivers +10.6% improvement on agent tasks and +8.6% on finance tasks, without any gradient updates. Here's what the architecture means for teams building production AI agents.
Read more02 Aug 2026 · 6 min read
ai-agents
An ETH Zurich study tested AGENTS.md files across hundreds of real-world GitHub issues and found that LLM-generated context files reduce task success rates by 3%, increase costs by 20%, and add nearly 4 extra reasoning steps per task. Here's what actually works — and why less structured context is usually better.
Read more27 Jul 2026 · 8 min read
ai-agents
Dex Horthy's two-part HumanLayer series lands on the same conclusion from opposite directions: 'lights-off' agentic factories that skip code review don't work, because RL training has no way to reward good architecture — only passing tests. The fix isn't less AI, it's front-loaded structure: research/plan/implement, frequent intentional compaction, and four review checkpoints before code gets written. Here's the synthesis and a rollout plan.
Read more16 Jul 2026 · 7 min read
ai-agents
Stateless agents are demos. Stateful agents are products. Here's the memory architecture stack that separates a useful AI agent from one that forgets everything between calls — and how to build it without rebuilding your whole infrastructure.
Read more28 Jun 2026 · 6 min read
ai-cost
Most AI cost overruns aren't about model pricing — they're about bloated context windows. Here's the architecture that helped teams cut AI costs by 80% without sacrificing output quality.
Read more24 Jun 2026 · 4 min read
agents
Prompt engineering gets you to demo. Context engineering gets you to production. Learn how controlling what information each agent receives determines whether your agentic system is reliable or brittle.
Read more09 May 2026 · 15 min read
agentic-ai
How the central question of building with AI has shifted three times in four years — from 'what should I say?' to 'what system should I build?' A deep dive into prompt engineering, context engineering, and harness engineering with architecture diagrams, decision frameworks, and production lessons for engineering leaders.
Read more18 Mar 2026 · 13 min read
agentic-ai
Most people are stuck in Phase 1 of AI — asking questions and doing work themselves. Phase 2 is Agents: you set a goal, the agent delivers results. Here's the complete breakdown of what changed, how it works, and why it matters.
Read more
