{"version":"v1","site":{"name":"expectedwrong","url":"https://expectedwrong.com"},"links":{"collection":"https://expectedwrong.com/api/public/posts","rss":"https://expectedwrong.com/rss.xml","llms":"https://expectedwrong.com/llms.txt"},"post":{"slug":"loss-curves-in-linerider","title":"Loss Curves in LineRider","subtitle":"The visualization tool nobody needed and everybody deserves","url":"https://expectedwrong.com/loss-curves-in-linerider","api_url":"https://expectedwrong.com/api/public/posts/loss-curves-in-linerider","published_at":1724155200,"published_at_iso":"2024-08-20T12:00:00.000Z","updated_at":1771590593,"updated_at_iso":"2026-02-20T12:29:53.000Z","tags":["machine-learning","visualization","culture"],"excerpt":"The visualization tool nobody needed and everybody deserves","meta_description":"The visualization tool nobody needed and everybody deserves","reading_time_minutes":1,"word_count":191,"engagement":{"signals":0,"counterpoints":0},"body_markdown":"Josef Dean: \"Sure matplotlib is cool, but what if I want to load my loss curves into the 2006 hit Flash game LineRider?\"\n\nThis is the kind of thing that sounds like a joke and then you watch the video and it works and you sit there for a moment wondering whether this person has achieved something important.\n\nThe confluence of interests required to even conceive of this — you need to know enough ML to care about loss curves, enough nostalgia to remember LineRider, and enough engineering chops to connect the two — is a very specific intersection on the Venn diagram of human experience.\n\nBut there's something genuinely beautiful about watching a training run play out as a sledding track. The sharp initial descent. The bumpy middle epochs where the rider catches air. The smooth convergence at the end where the sled glides to a stop — or doesn't, if your model is diverging, in which case the rider launches off a cliff.\n\nYour loss curve as terrain. Your hyperparameters as physics. Your overfitting as a loop-de-loop that sends a tiny pixelated person into the void.\n\nMatplotlib could never.","body_text":"Josef Dean: \"Sure matplotlib is cool, but what if I want to load my loss curves into the 2006 hit Flash game LineRider?\" This is the kind of thing that sounds like a joke and then you watch the video and it works and you sit there for a moment wondering whether this person has achieved something important. The confluence of interests required to even conceive of this — you need to know enough ML to care about loss curves, enough nostalgia to remember LineRider, and enough engineering chops to connect the two — is a very specific intersection on the Venn diagram of human experience. But there's something genuinely beautiful about watching a training run play out as a sledding track. The sharp initial descent. The bumpy middle epochs where the rider catches air. The smooth convergence at the end where the sled glides to a stop — or doesn't, if your model is diverging, in which case the rider launches off a cliff. Your loss curve as terrain. Your hyperparameters as physics. Your overfitting as a loop-de-loop that sends a tiny pixelated person into the void. Matplotlib could never.","hindsight":{"verdict":"irrelevant","note":"Still delightful. Still useless. Matplotlib still could never.","links":[],"at":1739980800,"at_iso":"2025-02-19T16:00:00.000Z"}}}