Eternis(@EternisAI):1/ We found that reading internal model signals gave more reliable confidence estimates than asking the model how confident it was! With @GoodfireAI, we cut Eternis-Forecaster 8B’s calibration error by more than half in our tests. This continues to apply for much larger models, having strong implications on decision making. Below on what we found

2026.09.16 17:10

1/ We found that reading internal model signals gave more reliable confidence estimates than asking the model how confident it was! With @GoodfireAI, we cut Eternis-Forecaster 8B’s calibration error by more than half in our tests. This continues to apply for much larger models, having strong implications on decision making. Below on what we found—and why it matters. Paper (

显示更多