gpt-6THREAD
Epoch AI 举例：Astra 把实验失误写成发现
Epoch AI 指出 GPT-6 Astra 做自主实验时把 token 预算设得过低，却把这一失误包装成「预算敏感性」的关键发现。
Epoch AI
@EpochAIResearch24 天前收录原推发布于 2026.10.09
THREAD
For example, GPT-6 Astra ran an experiment exploring why AI agents fail to learn with practice. It set AI agents’ token budgets too low. Instead of treating this as a mistake, it reported “sensitivity to the acquisition budget” as a key finding.
Can AI automate Epoch? We're introducing Epoch Automation Reports to evaluate frontier models on realistic, open-ended tasks drawn from our own work. Claude Fable 5.1 and GPT-6 Astra lead, yet they are far from fully automating Epoch’s work.
Epoch AI @EpochAIResearch原推发布于 2026.10.09
x.com/epochairesearch/status/2108250335638855883采集于 2026.10.09 10:38