Quote · Nerd Snipe with Theo and Ben
5 different models dropped last week & the GPT-5.6 usage limits are brutal
Where this was said
ClaudeX: Running GPT-5.6 Sol Inside Claude Code
At 2:06:04 · chapter starts 1:58:20
The episode's most practical and surprising conclusion: Theo now runs GPT-5.6 Sol inside Claude Code, not Codex, and it's dramatically better. The setup uses ViProxy, an open-source local proxy that authenticates multiple AI subscriptions and load-balances between them, as the bridge between Claude Code and the OpenAI API. A terminal alias called 'ClaudeX' hard-sets the model slug to GPT-5.6 Sol and routes through the proxy, giving Theo Claude Code's bounded workflow system running on OpenAI's most capable reasoning model. The efficiency gain is over 4× compared to Codex Ultra because workflows terminate by design. The moment when OpenAI's Tibo publicly quote-tweeted Theo's post asking for the recipe and blessing anyone who tried it is one of the funnier moments of the episode — implicit acknowledgment that the external community has found a better way to run OpenAI's own model than OpenAI's own harness. Both hosts close on the same observation: Claude Code was built for where models are going, Codex was built to patch where they were, and the gap has never been more visible.
Claude Code's workflow system writes a JavaScript file that defines bounded stages with typed outputs, so subagents have a defined end. Codex Ultra spawns subagents dynamically mid-execution with no cap, each potentially spawning more. The workflow has an ending — Ultra doesn't.
Theo built a terminal alias called 'ClaudeX' that routes GPT-5.6 Sol through a proxy into Claude Code, combining the best subagent workflow system with the most powerful reasoning model. OpenAI's Tibo publicly blessed the setup and offered free resets to anyone who got banned trying it.
Theo found that using Claude Code workflows with GPT-5.6 Sol was over 4× more token efficient than running the same tasks through Codex Ultra due to bounded subagent spawning.