GPT-6 Astra and GPT-6.1 Sol can execute low-probability actions without CoT
Astra and Sol can take low probability actions with no CoT
The authors reproduced the experiments of Serrano et al., 2026 and found that GPT-6 Astra and GPT-6.1 Sol can execute low-probability actions in a single forward pass without chain of thought, calibrated to the target probability. When the user prompt was repeated 3 or 5 times, and with filler tokens added, both were well calibrated and gave completely identical responses to the same UUIDv4; with implicit prompting they did not output A at all. GPT-5.6 Sol was poorly calibrated, and Fable 5, Gemini 3.1 Pro, and Jev never output A at target probabilities of 10% and 1%. The authors speculate that Astra and GPT-6.1 Sol may decide whether to output A based on the first 4 bytes of the UUID, but could not determine their internal algorithm.
The authors reproduced the low-probability action experiments and found that Astra and Sol can achieve probability calibration in a single forward pass, providing a data point for no-CoT monitorability evaluation.