pith. sign in

← back to paper

Review history

arxiv: 2605.22672 · 2 revisions

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most

  1. 2026-05-25 UNVERDICTED MODERATE v0.9.0 novelty 7.0
    43352 ms 5752 in 1412 out 2026-05-25T06:00:47.636695+00:00
  2. 2026-05-22 CONDITIONAL LOW v0.9.0 novelty 6.0
    40098 ms 5752 in 1195 out 2026-05-22T05:19:21.068438+00:00