GPT-6 Astra 仅靠计算工具即可审计临床预测网络，无需直接读取权重
Computation, not weight access: large language models as auditors of clinical prediction networks
实验设计挺巧的：给 GPT-6 一个只能算数不能读权重的工具，审计临床模型的效果和白盒一样好，对做模型审计的人很有参考价值。
一项仿真实验测试了 GPT-6 Astra 等 5 个 GPT 模型能否从文件层面审计临床预测模型。在无工具条件下，Astra 只能处理 353 权重网络，超过 3,457 权重即不可靠，且默认指令下拒绝 12 项任务中的 11 项。接入仅暴露网络预测的黑盒计算工具后，它在全部 29 次、最高 38,401 权重的实验中找出了植入关系，并在 6 次实验中发现标签少报死亡的偏置亚组。黑盒与白盒访问效果相当，说明审计关键在于计算能力与提示设计，而非读取原始权重。
Computation, not weight access: large language models as auditors of clinical prediction networks
Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files alone. Public demonstrations, however, mixed reading raw weights with running code. We separated these conditions in internally pre-specified simulation experiments. Tanh networks of 105 to 38,401 weights were trained on simulated cohorts of patients with subarachnoid haemorrhage, each with a planted relationship or none, and one network was trained on labels that under-recorded deaths in a subgroup. GPT-6 Astra and four other GPT models answered single prompts under a default or an explicit system instruction, either with the weights in the prompt and no tools, or with a calculation-only tool that exposed the weights (white box) or only the network's predictions (black box). Without tools, Astra recovered planted relationships in 353-weight networks but became unreliable at 3,457 weights, and under the default instruction it declined 11 of 12 audit and repair tasks as unidentifiable; the explicit instruction removed these refusals. With the tool, it recovered the planted relationship in all 29 runs on networks of up to 38,401 weights, raised no false alarm in 15 runs on null networks, and found the biased subgroup in 6 of 6 runs. Black-box access performed as well as white-box access, and other GPT-6 models read as accurately. A well-designed script matched the comparator models on the audit and the best LLM repair. For auditing these networks, what mattered was computation and elicitation, not access to the weights.
