Anti-Distillation Safeguards Cut Exposed Reasoning Tokens from 8,800x to 135x
zainhas · x · 2026-10-13
zainhas shared a log-scale chart of 'reasoning tokens exposed to distillers.' Before full safeguards, daily reasoning tokens exposed to successful distillation requests averaged 8,800x the quietest day (peaking at 56,000x); after safeguards went fully on (September 19), the average dropped to 135x, with several days too low to measure. The data quantifies how effectively labs' anti-distillation protections cut reasoning-chain leakage — though some leaky days remain.
More from Models
- Meta's Muse Wonder (Max) tested on one-shot 3D scenes and front-end vs top models — arena · 2026-10-13
- Five Ways to Monetize Open-Weight LLMs, API Sales Lead — Terminator857 · 2026-10-13
- Quintin Pope: pretraining is a degenerate special case of RL, subsumed by RL with right data — QuintinPope5 · 2026-10-13
- Muse Code coding model impresses in early testing: faster than Claude Code — QuixiAI · 2026-10-13
- 1.2M Calls Study: Even at Temperature 0, LLM Benchmarks Vary Up to 24% — lulzxdxdxd · 2026-10-13
- "Another benchmaxxed release in 14 hours": AI circle mocks benchmark hype — thesaraharminta · 2026-10-13