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.
More from coding & agent
- Adobe MAX: MCP across Creative Cloud, AI agents editing layers, Firefly Builder and Graph — umesh_ai · 2026-11-11
- Sydney Codex Community Buildathon set for Nov 14 with Cerebras-backed ultrafast compute track — paw_lean · 2026-11-11
- shadcn's improve hits 10k stars: let top models plan, cheap models execute code fixes — shadcn · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Claude Opus 5.5 runs an architecture search and finds AttnRes-Canon, a new top Transformer design — SonglinYang4 · 2026-11-11
- 5 research habits worth knowing: read papers backwards, reproduce first, wire coding agents via MCP — cneuralnetwork · 2026-11-11