Hacker News
- Leakage and the reproducibility crisis in ML-based science https://reproducible.cs.princeton.edu/ 37 comments
Linking pages
- GPT-4 and professional benchmarks: the wrong answer to the wrong question https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks 329 comments
- Beware of AI pseudoscience and snake oil – Baldur Bjarnason https://www.baldurbjarnason.com/2023/beware-of-ai-snake-oil/ 178 comments
- Machine learning is useful for many things, but not for predicting scientific replicability https://www.aisnakeoil.com/p/machine-learning-is-useful-for-many 37 comments
- AI leaderboards are no longer useful. It's time to switch to Pareto curves. https://www.aisnakeoil.com/p/ai-leaderboards-are-no-longer-useful 14 comments
- What we know about machine learning's replication crisis https://youneskamel.substack.com/p/what-we-know-about-machine-learnings?s=w 6 comments
- Introducing the AI Snake Oil book project https://aisnakeoil.substack.com/p/introducing-the-ai-snake-oil-book 1 comment
- The bait and switch behind AI risk prediction tools https://aisnakeoil.substack.com/p/the-bait-and-switch-behind-ai-risk 0 comments
- The Curse of Performative User Studies | Aaron Hertzmann’s blog https://aaronhertzmann.com/2023/04/27/user-studies.html 0 comments
- A sneak peek into the book https://aisnakeoil.substack.com/p/a-sneak-peak-into-the-book 0 comments
- Introducing the REFORMS checklist for ML-based science https://www.aisnakeoil.com/p/introducing-the-reforms-checklist 0 comments
- Will AI transform law? https://www.aisnakeoil.com/p/will-ai-transform-law 0 comments
Related searches:
Search whole site: site:reproducible.cs.princeton.edu
Search title: Leakage and the Reproducibility Crisis in ML-based Science
See how to search.