@simonwillison.net To mitigate the (pernicious) effects of bike-pelicanmaxxing that's widespread in current-generation LLMs, I propose a new benchmark of "A Pelican waiting in line to get fish and chips" as per youtu.be/grIJjMCh0cw?...
youtu.be
Pelican Waiting in Line for Fish & Chips
YouTube video by Jack Simpson
![Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
Anneliese Riess, Juan Felipe Gomez, Flavio du Pin Calmon, Julia Anne Schnabel, Georgios Kaissis
http://arxiv.org/abs/2602.04562
We prove the conjecture stated in Appendix F.3 of [Zhu et al. (2022)]: among all conversion rules that map a Rényi Differential Privacy (RDP) profile $τ\mapsto ρ(τ)$ to a valid hypothesis-testing trade-off $f$, the rule based on the intersection of single-order RDP privacy regions is optimal. This optimality holds simultaneously for all valid RDP profiles and for all Type I error levels $α$. Concretely, we show that in the space of trade-off functions, the tightest possible bound is $f_{ρ(\cdot)}(α) = \sup_{τ\geq 0.5} f_{τ,ρ(τ)}(α)$: the pointwise maximum of the single-order bounds for each RDP privacy region. Our proof unifies and sharpens the insights of [Balle et al. (2019)], [Asoodeh et al. (2021)], and [Zhu et al. (2022)]. Our analysis relies on a precise geometric characterization of the RDP privacy region, leveraging its convexity and the fact that its boundary is determined exclusively by Bernoulli mechanisms. Our results establish that the "intersection-of-RDP-privacy-regions" rule is not only valid, but optimal: no other black-box conversion can uniformly dominate it in the Blackwell sense, marking the fundamental limit of what can be inferred about a mechanism's privacy solely from its RDP guarantees.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:bvdt4psvley2chbqednjkkw2/bafkreibvlh3n7i3ederxrbukszvhylc25xkrpgww26ey6nctc5ynydmvma)
