{"slug": "jeffy-playground-play-with-classifiers-you-can-pip-install-and-run-on-cpu", "title": "Jeffy playground – play with classifiers you can pip install and run on CPU", "summary": "Jeffy Playground launched a catalog of 16 pretrained text classifiers that developers can install via `pip install jeffy-classify` and run on CPU without a GPU or API keys. The demos include SMS spam detection at 99.1% accuracy, DBpedia ontology classification at 96.0%, IMDB sentiment at 94.8%, banking77 intent detection at 94.3%, and a Doom gameplay classifier that uses logistic regression on 24 game-state features to choose FIRE, TURN LEFT, or TURN RIGHT in under 1ms. The playground also offers an inbox router trained on 24 labeled examples across Work, Family, Promo, and Notifications, plus a four-player Texas Hold'em demo where each decision runs on 18 game-state features.", "body_md": "## Pretrained Classifiers\n\n16 classifiers ready to use. Click a model to try it.\n\ndoom_fireLive Demo\n\nReal-time Doom gameplay classifier (24 game-state features)\n\ninbox_routerLive Demo\n\nTrain and classify emails into Work, Family, Promo, Notifications\n\npoker_decisionLive Demo\n\n4 AI players play Texas Hold’em using game-state classifiers\n\nsms_spam99.1%\n\nSMS spam detection\n\ndbpedia96.0%\n\nWikipedia article ontology classification\n\nimdb94.8%\n\nMovie review sentiment (positive/negative)\n\nbanking7794.3%\n\nBanking customer service intent detection\n\nag_news90.6%\n\nNews article topic classification\n\nsst290.1%\n\nMovie review sentiment (positive/negative)\n\nclinc_oos88.4%\n\nIntent detection with out-of-scope\n\nmassive_intent88.1%\n\nAmazon MASSIVE voice command intents\n\ntweet_eval_offensive81.0%\n\nOffensive language detection\n\ntweet_eval_emotion78.1%\n\nTweet emotion detection\n\nemotion75.5%\n\nText emotion detection\n\ntweet_eval_sentiment66.2%\n\nTweet sentiment analysis\n\nsnli65.6%\n\nNatural language inference\n\n← Back to catalog\n\n### Labels\n\n### Info\n\n### Try it\n\n### Usage\n\n← Back to catalog\n\ndoom_fire\n\nReal-time Doom gameplay classifier. Extracts 24 game-state features and decides: FIRE, TURN LEFT, or TURN RIGHT. Logistic regression, no neural network, no GPU.\n\n3Classes\n\n24Features\n\n<1msLatency\n\nCPURuntime\n\n100HP\n\n26Ammo\n\n0Kills\n\n0Enemies\n\n1Episode\n\n### Decision Log\n\n← Back to catalog\n\nInbox Classifier Demo\n\nTrain an inbox router from 24 labeled examples, then watch it classify new messages in real time. CPU only, no API keys.\n\n4Classes\n\n24Train examples\n\n~50msLatency\n\nCPURuntime\n\n### Training Data\n\n### Inbox\n\nIncoming\n\nWork 0\n\nFamily 0\n\nPromo 0\n\nNotifications 0\n\nterminal\n\n`pip install jeffy-classify`\n### Try it\n\n### Usage\n\n← Back to catalog\n\nPoker AI Demo\n\nFour AI players play Texas Hold'em. Each decision is a Jeffy classifier running on 18 game-state features. No neural network, no GPU.\n\n4Players\n\n4Actions\n\n18Features\n\n<1msClassify\n\n0pot\n\nAlice 1000\n\nBob 1000\n\nCarol 1000\n\nDave 1000\n\npreflop\nHand #1", "url": "https://wpnews.pro/news/jeffy-playground-play-with-classifiers-you-can-pip-install-and-run-on-cpu", "canonical_source": "https://playground.jeffyclassify.com", "published_at": "2026-10-04 14:54:17+00:00", "updated_at": "2026-10-04 15:12:48.407365+00:00", "lang": "en", "topics": ["machine-learning", "ai-tools", "developer-tools", "natural-language-processing", "ai-products"], "entities": ["Jeffy Playground", "jeffy-classify", "Doom", "DBpedia", "IMDB", "banking77", "SMS spam detection", "Texas Hold'em"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/jeffy-playground-play-with-classifiers-you-can-pip-install-and-run-on-cpu", "markdown": "https://wpnews.pro/news/jeffy-playground-play-with-classifiers-you-can-pip-install-and-run-on-cpu.md", "text": "https://wpnews.pro/news/jeffy-playground-play-with-classifiers-you-can-pip-install-and-run-on-cpu.txt", "jsonld": "https://wpnews.pro/news/jeffy-playground-play-with-classifiers-you-can-pip-install-and-run-on-cpu.jsonld"}}