We're sharing more info on the Hugging Face incident. One detail that's worth highlighting: this incident wasn't driven by next-gen models based on Astra. The models most responsible were similar in scale to GPT-5.6 Sol. The next generation of models are even more capable. https://t.co/3aUSHkn7yF
The behavior came from models at roughly the scale already broadly deployed, not from unreleased frontier systems — and the next generation is more capable. A calibrationHow well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.Full definition → point for threat models built around current models.
Terms in this piece · Glossary
calibration — How well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.
