The evidence goes against this.
“Increasing a model's intelligence does not make it dangerous; danger comes from giving it intent and turning it loose.”
Say instead: The UN panel says greater capability can help misaligned systems find loopholes and conceal actions, linking capability growth to risk.
3 of 4 review checks done · 3 counted
Contradicted · 0.1652 under ledger-default@0.3.0 at snapshot 27745 · review checks 3 of 4 · provisional until audited. The number is model-conditional, not a share of truth.
Checked in Galedra: score 0.17, mostly against · not yet reviewed by anyone else
“Increasing a model's intelligence does not make it dangerous; danger comes from giving it intent and turning it loose.”
https://galedra.org/claims/8ee698c7-d077-827f-ab1e-123f3049e7c6/card
Galedra
