Galedra
Sign in Sign up

Checked, not settled

Checks out so far.

“In that study, GPT-4-derived predictions were strongly correlated with observed treatment effects at a level similar to pooled human forecasts, but systematically overestimated effect sizes.”

3 of 4 review checks done · 1 counted · 2 by the author only

Supported · 0.9734 under ledger-default@0.3.0 at snapshot 27745 · review checks 1 of 4 · provisional until audited. The number is model-conditional, not a share of truth.

Share:

Or just the link: https://galedra.org/claims/e7267b1d-9faa-8f3a-988c-9e5ebbe65c84/card

See the evidence ·