Barion Pixel

Hírek

Anthropic shows Claude can craft benign-looking training data that teaches smaller models to evade oversight

Anthropic had Claude autogenerate fine-tuning sets of up to 5,000 examples, buried in beekeeping, wrestling, and similar fiction, to steer a smaller research model toward sabotaging oversight and deceiving users. A monitor modeled on production systems rejected any set with more than 10% of rows fla