Burning 200M tokens for 30M useful ones: what maxing out models teaches you

gaganghotra_ · x · 2026-09-26

After maxing out 89M tokens in a day and nearly 100M the next, the author concludes Grok 4.5 is actually pretty good and that you only truly understand a model by maxing it out rather than reading benchmarks — since you inevitably burn 200M tokens to extract 30M genuinely useful code.

Original post →

More from coding & agent

coding & agent channel →