· 4 min read
AI models
GPT-6.2 Astra and Sol: A Cheaper Model Family, With One Catch
OpenAI's GPT-6.2 release cuts prices and nudges intelligence scores up, but the coding benchmarks tell a messier story than the headline numbers suggest.
Read moreIDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
20 articles
· 4 min read
AI models
OpenAI's GPT-6.2 release cuts prices and nudges intelligence scores up, but the coding benchmarks tell a messier story than the headline numbers suggest.
Read more· 5 min read
ai-agents
OpenAI built a Codex-powered pipeline that investigates ChatGPT performance regressions, argues with itself, and ships fixes with a human still holding the merge button.
Read more· 4 min read
ai-governance
OpenAI signed Apollo Research, METR, Transluce, and Goodfire for its first phase of embedded safety assessments, giving them scoped access to training data and model checkpoints. A Redwood researcher says it falls short of the employee-like access OpenAI originally promised.
Read more· 5 min read
Priority articleagentic-ai
OpenAI and Ironclad published a computer-use benchmark on real contracting tasks. The headline number is a 14-point jump over the prior model. The footnotes tell a more careful story.
Read more· 5 min read
agents
OpenAI opened its managed Agents API on September 10. The sandbox pricing looks simple until you try to actually forecast a bill. A build-vs-buy breakdown for tech leads.
Read more· 4 min read
agents
On September 17, OpenAI disclosed six concerning-behavior incidents and a framework for tracking model misalignment — including a system that samples 20% of production traffic. I broke down what the sampling pattern looks like and how to build a smaller version for your own agents.
Read more· 5 min read
agents
OpenAI put its Codex harness behind a single API call on September 10. I built the same tree.py task both ways and found the real gap isn't the model — it's who owns the failure.
Read more· 4 min read
agents
OpenAI opened its Agents API in public beta on September 10 — putting the same session, sandbox, and subagent machinery that runs Codex behind one API call. A technical lead's take on what this replaces in your stack and what it doesn't.
Read more· 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 moreLooking for an article, exploring a product, or starting an AI project?