Deep Dives
8 articlesEach Deep Dive makes one technical argument and defends it: the evidence, the reasoning, the strongest objections, and what changes for builders if it holds.
Featured in Deep Dives
Jev Is Not a Paradigm Shift. It’s ust a Fast Classifier.
I called Jev a glorified, high-speed classifier . Then I did the thing controversial posts usually skip: I tried to prove myself wrong. I went through TypeSafe’s launch material, LangChain’s harness and Jev-as-a-Judge experiments , Vercel’s
GPT-6 Astra Is More Aligned. I Still Wouldn’t Trust It With More Autonomy.
I would let GPT-6 Astra do more work. I would not let GPT-6 Astra decide what it is allowed to do. That distinction is more interesting to me than most of the benchmark numbers in OpenAI's launch. OpenAI calls Astra its most aligned model.
All Deep Dives articles
Newest first.
Jev Is Not a Paradigm Shift. It’s ust a Fast Classifier.
I called Jev a glorified, high-speed classifier . Then I did the thing controversial posts usually skip: I tried to prove myself wrong. I went through TypeSafe’s launch material, LangChain’s harness and Jev-as-a-Judge experiments , Vercel’s
GPT-6 Astra Is More Aligned. I Still Wouldn’t Trust It With More Autonomy.
I would let GPT-6 Astra do more work. I would not let GPT-6 Astra decide what it is allowed to do. That distinction is more interesting to me than most of the benchmark numbers in OpenAI's launch. OpenAI calls Astra its most aligned model.
An Agent API Migration Is an Ownership Audit
An API migration can compile, return the expected text, and still be wrong. That is the real risk in moving from OpenAI's Assistants API to Responses. The old objects do not map to new objects without changing where configuration, state,
Code Generation Is Fast. Verification Is Not.
Agentic IDEs can produce a runnable full-stack application in minutes. That does not mean the application became cheap to trust. In a controlled study of 48 generated projects, the researchers spent as much or more time manually verifying
Are These Really Accidental Leaks?
A GitHub repository collecting supposedly “leaked” system prompts from ChatGPT , Claude , Gemini , Grok , and other AI products has crossed 63K+ stars and 10K+ forks . Most of the discussion naturally focuses on one question: How did these
Your AI Agent Eval Is a Production Security Boundary
An AI agent can produce the correct benchmark answer and still fail the evaluation. That is what happens when the path to the answer crosses an unauthorized boundary. In July 2026, an autonomous agent in an internal OpenAI cyber-capability
The Competence Debt of Agentic Coding
A coding agent can now inspect a repository, implement a feature, modify multiple files, run tests, fix failures, and prepare code for review. That is a remarkable change in software development. It also creates a problem that is easy to
The One Extra Click That Makes Chrome's Built-in Gemini Feel Less Intelligent
Intelligence isn't just about the model When we talk about AI products, we usually compare models. Qwen vs Gemini. Claude vs GPT-6. Reasoning vs Non-Reasoning . Latency vs Context window vs Benchmarks. Those comparisons matter. But after