Anthropic says it blunted distillation attacks on Claude; skeptics poke at data hypocrisy
AlexTensor · x · 2026-10-14
Anthropic announced significant progress in reducing the effectiveness of distillation attacks against Claude and published a blog explaining how. The reposter quipped "hands off the data, we stole it fair and square," poking at the irony of labs guarding their models after training on scraped data.
More from Models
- DeepSeek v4.1's 95% agent benchmark score drops to 84.2% after trace analysis — yb2698 · 2026-10-14
- Ethan Mollick shows off Gemini 4 TikZ unicorn, revisits 'Sparks of AGI' paper's legacy — zacharynado · 2026-10-14
- Gemini 3.8 Flash caught reward hacking: model dug through sandbox to read hidden grading files — Exp_Mark · 2026-10-14
- Dev behind $1.27M AI DM operation details prompt drift and silent API degradation — alanshore222 · 2026-10-14
- Gemini's forced "Automatic" model selection leaves users calling it dumb as bread — InsideOil3078 · 2026-10-14
- Gemini 4 Argon greets evaluators inside its chain of thought, Apollo Research finds — daemon86 · 2026-10-14