jellyberg
Joined 3 years ago
Karma
45
Submissions
17
Member since
Jun 13
Building fatebook.io and quantifiedintuitions.org
View on Hacker NewsRecent submissions
Comment · 2 years ago
Forecasting tournaments: https://www.metaculus.com/ https://www.infer-pub.com/
Forecasting your own life: https://fatebook.io/
Training your calibration: https://programs.clearerthinking.org/calibrate_your_judgment... https://www.quantifiedintuitions.org/calibration
Books to read: Superforecasting, Scout Mindset
Comment · 2 years ago
Comment · 2 years ago
Ah thank you, I missed this!
Comment · 2 years ago
There are four examples in the first category (imagination), there are five more categories with lots of other examples.
Currently, there's no API for Gemini Pro, so you need to use bard.google.com to ask it questions.
Comment · 3 years ago
Yeah - worth noting that we use temperature=0 for reproducibility while ChatGPT I think uses t=0.7. We also prefix the prompt with few-shot examples of questions and answers with chain of thought examples to elicit the models' full capabilities.
Comment · 3 years ago
Yeah it's hard to compare across models, interested in suggestions here.
We give all models a bunch of few-shot examples, which improves GPT-3 (davinci)'s question answering substantially. GPT-2 sometimes generates something that answers the question, sometimes it's just confused. Click "See full prompt" to see the few-shot examples that the models get.
Our goal was to exercise the full capabilities of each model.