Jeffy playground – play with classifiers you can pip install and run on CPU

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.

Pretrained Classifiers 16 classifiers ready to use. Click a model to try it. doom fireLive Demo Real-time Doom gameplay classifier 24 game-state features inbox routerLive Demo Train and classify emails into Work, Family, Promo, Notifications poker decisionLive Demo 4 AI players play Texas Hold’em using game-state classifiers sms spam99.1% SMS spam detection dbpedia96.0% Wikipedia article ontology classification imdb94.8% Movie review sentiment positive/negative banking7794.3% Banking customer service intent detection ag news90.6% News article topic classification sst290.1% Movie review sentiment positive/negative clinc oos88.4% Intent detection with out-of-scope massive intent88.1% Amazon MASSIVE voice command intents tweet eval offensive81.0% Offensive language detection tweet eval emotion78.1% Tweet emotion detection emotion75.5% Text emotion detection tweet eval sentiment66.2% Tweet sentiment analysis snli65.6% Natural language inference ← Back to catalog Labels Info Try it Usage ← Back to catalog doom fire Real-time Doom gameplay classifier. Extracts 24 game-state features and decides: FIRE, TURN LEFT, or TURN RIGHT. Logistic regression, no neural network, no GPU. 3Classes 24Features <1msLatency CPURuntime 100HP 26Ammo 0Kills 0Enemies 1Episode Decision Log ← Back to catalog Inbox Classifier Demo Train an inbox router from 24 labeled examples, then watch it classify new messages in real time. CPU only, no API keys. 4Classes 24Train examples ~50msLatency CPURuntime Training Data Inbox Incoming Work 0 Family 0 Promo 0 Notifications 0 terminal pip install jeffy-classify Try it Usage ← Back to catalog Poker AI Demo Four AI players play Texas Hold'em. Each decision is a Jeffy classifier running on 18 game-state features. No neural network, no GPU. 4Players 4Actions 18Features <1msClassify 0pot Alice 1000 Bob 1000 Carol 1000 Dave 1000 preflop Hand 1