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
How to Survive Your $200 Codex Plan: Fast Mode, Reasoning Levels, and Stopping Points
At 1:24:20 · chapter starts 1:10:00
This is the most immediately actionable chapter of the episode, built around Theo's publicly posted article on usage optimization. Fast Mode is the easiest and most impactful fix: it costs 2.5× more usage for a speed improvement that feels minimal given how much time Sol spends waiting on tool calls rather than generating tokens. The reasoning level hierarchy — Low through Max — gets a detailed treatment using an analogy to Intel CPU overclocking: X-High and Max are like the motherboard manufacturer overriding the chip's thermal limits to score better on benchmarks, burning through headroom for a 1–2% score improvement that disappears in real-world use. High is the sweet spot. The most underrated tip is prompt discipline: Sol will run indefinitely unless you write an explicit stopping point into your prompt. Unlike Fable, which naturally stops and checks in, Sol is a Rottweiler that needs a leash in the form of a sentence like 'stop after the first round of reviews and ask me questions.'
Ben ran a single PR review in Ultra mode and it consumed 50% of his weekly usage allowance over a 2-hour session, spawning approximately 40 top-level subagents.
Turn off Fast Mode (2.5× usage multiplier for only 50% speed gain), stay between Low and High reasoning (X-High and Max exist only for benchmarking), tell the model explicitly where to stop, and never use Ultra. These four changes alone can make a $200 plan feel unlimited again.
