Evals @simile_ai | prev: stat phd @UCBerkeley, @BrownUniversity, @Amazon
Joined June 2023
- Tweets36
- Following143
- Followers566
- Likes240
A Walden (1854) quote for the AI era…
“Up come the books, but down goes the wit that writes them.” 😩
Exclusive: Another prestigious award has gone to a writer who seems to have used AI as the crisis of trust in the literary world intensifies, @vauhinivara reports: theatlantic.com/books/2026/1…
I just joined @simile_ai last week to help build out their confidence model! It's an exciting real world application of uncertainty quantification :) Check out our blog post to learn more about the progress that's been made so far, led by the amazing @wesel0
Anyone can simulate the future. But the simulation only matters if it’s trustworthy.
At Simile, we train two types of models: simulation models and confidence models. Our first research blog post explores the origin of our proprietary confidence model, which predicts the accuracy of our population simulations and, in turn, makes them actionable.
simile.com/blog/confidence?v…
In the liminal period between my PhD and starting my job, I’ve been going through my backlog of photos. It’s reminded me that one thing AI will never be able to do for us is *experience wonder*… so go touch grass! Feel joy! Love the world & the life that inhabits it
Some faves:
viii. I caught many beautiful Berkeley sunsets throughout my PhD, including this one from the Berkeley Marina. It seems fitting to end with a sunset pic as one chapter of my life closes and the next begins! (Berkeley, California, 2022)
🫡Ok, thanks for indulging me and sharing in my moments of wonder. More here! tiffanyding.github.io/photo/…
i. Desert twilight at Arches National Park (Moab, Utah, 2021)
ii. New life, still untouched by the dust that burdens its elders (Northern California Coast, 2024) xitter.cf/tifding/status/2086870…
Graduated! Very grateful for my advisors, Mike Jordan and Ryan Tibshirani, who set the Pareto frontier for brilliance and kindness 🧠🩷
Next stop: MIT for a postdoc with @stats_stephen!
Come say hi at my @iclr_conf poster (Friday 10:30am, Pavilion 3 #316) to chat about prediction sets or why @PlantNetProject is my favorite plant identification app!
New paper: Conformal prediction for long-tailed classification🐒
arxiv.org/abs/2507.06867
🧑🌾 (plant enthusiast): Help me identify plants!
🤖 (existing conformal algs): Do you want sets that never include rare plants or sets that contain 100s of labels?
🧑🌾: Uhh… neither? A🧵(1/n)
My collaborator Joseph Salmon made a beautiful blog post about our paper, featuring an *interactive* recreation of a figure from Sadinle, Lei & Wasserman's iconic 2019 conformal prediction paper. Go check it out!
Blog post: josephsalmon.eu/blog/long-ta…
New paper: Conformal prediction for long-tailed classification🐒
arxiv.org/abs/2507.06867
🧑🌾 (plant enthusiast): Help me identify plants!
🤖 (existing conformal algs): Do you want sets that never include rare plants or sets that contain 100s of labels?
🧑🌾: Uhh… neither? A🧵(1/n)
New paper: Conformal prediction for long-tailed classification🐒
arxiv.org/abs/2507.06867
🧑🌾 (plant enthusiast): Help me identify plants!
🤖 (existing conformal algs): Do you want sets that never include rare plants or sets that contain 100s of labels?
🧑🌾: Uhh… neither? A🧵(1/n)
All of these tools lead to strong empirical performance on PlantNet and iNaturalist. Check out the looooong tail; this is a tough setting! Some classes are left with 0 holdout examples for calibration (4/n)
This is joint work with Jean-Baptiste Fermanian & Joseph Salmon and inspired by discussions with the rest of the @PlantNetProject team (p.s. Check out their awesome plant identification app if you haven’t yet!🌱) (n/n)