srush roast: interpretability blogs are the recipe blogs of ML
srush_nlp · x · 2026-10-16
NLP researcher Sasha Rush quipped that interpretability blogs are "the recipe blogs of ML" — you have to wade through the story of someone's grandmother's first house before learning they used gradients. His tongue-in-cheek fix: "just put the mechanism in the bag bro." A widely relatable jab at bloated ML blog writing.
Related event: Sasha Rush Mocks Interpretability Blogs for burying the Point in Stories(2 posts)→
More from Fun
- Rare 1985 photo shows Paul Erdős with 10-year-old Terence Tao — yassineyousfi_ · 2026-10-17
- Dev shows his wife their AI project's UI; her reaction becomes a meme — tekbog · 2026-10-17
- Software engineer: devs are now just glorified agent managers — KevinNaughtonJr · 2026-10-17
- Dev complains coding agents force him to live in the terminal he hates — pixlpa · 2026-10-17
- Fully local AI video generation with Claude as the director — No_Mud2447 · 2026-10-17
- Generate AI video in 480p then upscale? Debate over credit-saving trick — adrianscottcom · 2026-10-17