The blog.
8 posts on openaiRSS feed
Haiku 5.5 vs GPT-6 Luna: The Benchmarks Lied
Anthropic's benchmarks said Haiku 5.5 crushes OpenAI's GPT-6 Luna. I ran them head-to-head on the same prompts and harness — and the real-world results told a completely different story.
GPT-6.1 Sol vs Sonnet 5.5: Which One Actually Wins?
OpenAI's GPT-6.1 Sol posts insane benchmarks at a fraction of the cost. I ran it head-to-head against Sonnet 5.5 across four real builds to see if the numbers hold up.
ChatGPT Dots: Early Access Review and How It Works
I got early access to OpenAI's new Dots — an always-on cloud AI agent powered by GPT-6 Astra. Here's how it works, how it compares to Muse and Grokbot, and who actually needs it.
GPT-6 Soul & Luna: Cheaper Models That Still Deliver
OpenAI's GPT-6 Soul and Luna trade a few benchmark points for massive cost savings. Here's what the numbers actually say and when to reach for each one.
GPT-6 Astra vs Fable 5.1: What Actually Matters
OpenAI's GPT-6 Astra matches or beats Anthropic's Fable 5.1 on most benchmarks at a lower price. Here's what actually matters for people who build with these models.
Codex Goals: The Autonomous Coding Loop Claude Code Doesn't Have
Codex's experimental Goals feature is a built-in Ralph loop — single slash command, no orchestration layers, runs autonomously for hours. Here's how it works and how to set it up.
How to Use Claude Code and Codex Together (Stop Choosing)
Stop trying to pick between Claude Code and Codex. The smarter play is running both — Codex desktop with Claude Code in the terminal inside it. Here's the exact setup, pricing, and dual-model workflow.
Claude Code + Codex Plugin: Adversarial Review and Rescue Mode
OpenAI's Codex plugin runs inside Claude Code. Get adversarial code review, rescue mode, and a second pair of AI eyes on production code.
