Did SuperGrok Cut Limits Again? 900k Tokens Burned on Cold Starts and Cache Misses
NickPassig · x · 2026-11-11
A paying user questions whether SuperGrok lowered its usage limits again: 50% consumed in a single day. The author breaks down where the tokens went — roughly 900k tokens were "the sum of a repeated cold start, two cache misses, and a source-code search to point at a file that was already on disk," suggesting much of the quota burn is engineering overhead rather than actual output.
More from Models
- Agent Arena: Gemini 4 Carbon Gets More Cost-Competitive as Tasks Get Harder — rseroter · 2026-11-11
- LiquidAI's 1.7B LFM3 hits SOTA on Multi-IF, beating 100x-larger rivals including ERNIE 5.0 — NielsRogge · 2026-11-11
- Fable 5.2 tops GDPx chip-design benchmark, but task authors see zero gains — ycombinator · 2026-11-11
- 1.3B open-source MiniCPM-OCR 1.0 tops Real5-OmniDocBench, beating GPT-5.2 — NielsRogge · 2026-11-11
- Claude writes dark, offensive jokes freely while GPT censors them, per hands-on test — ivan_bezdomny · 2026-11-11
- Dev trains a 944K-param autocomplete model on Enron emails for 35 cents — victormustar · 2026-11-11