Walkthroughs, demos, and deep dives. Our notes first, the original next.
The full collection
197 videos · showing 145–168
Alex Hitt demonstrates deploying the open-source Jev Trader bot on Monad testnet. The walkthrough covers provider credentials, separate RPC paths for reads and writes, network timing, decision telemetry, and dry-run quote placement before live orders.
Duration: 6 minutes 32 seconds.Brandon Roberts explains TypeSafe AI's Jev model as a fast system-one decision engine. He reviews core differences from traditional chat LLMs, examines platform primitives like choices, scores, and booleans, and demonstrates an automated GitHub issue triage CLI script using the TypeSafe SDK.
Duration: 13 minutes 36 seconds.Dan Vega demonstrates how to interact with TypeSafe's Jev decision model using standard HTTP requests. He covers Jev's core primitives (Noul/boolean, choice, score) and shows how to call the REST endpoint using plain Java 25 HttpClient and Spring Boot RestClient with Java records.
Duration: 25 minutes 51 seconds.This video breaks down TypeSafe's non-generative Jev decision model, analyzing how parallel evaluation replaces autoregressive generation for software loops. It critically examines vendor-reported speed and cost claims against practical cheap-model routing, highlighting operational trade-offs and vendor eval caveats.
Duration: 7 minutes 31 seconds.EDteam explains Jev's architecture as a probability-based decision engine rather than a generative text LLM. They cover API payload design (state, questions, criteria) across choice, Noul, and score question types, run playground experiments highlighting prompt sensitivity, and showcase an MVP course recommender sorting real catalog entries using confidence scores.
Duration: 25 minutes 11 seconds.Fazt explores TypeSafe AI's Jev decision model, explaining its typed primitives (Noul, choice, score) and batch queries over state context. He builds a practical ticket triage application demonstrating automated classification and priority scoring.
Duration: 30 minutes 50 seconds.Ryan Vogel explains Jev, a specialized classification model by TypeSafe AI that outputs probabilities across schema options. He showcases fast email triage, lead routing, video clip detection, and browser automation, while detailing limitations on tasks requiring broader intelligence like trading.
Duration: 28 minutes 24 seconds.Hunter Bohm evaluates TypeSafe's Jev model, explaining its parallel structured schema scoring and non-generative nature. He explores community use cases like dispatch routing and computer use, then presents hybrid tests pairing Jev with Astra to offload code review, email classification, and browser steps to cut agent runtime and API costs.
Duration: 12 minutes 39 seconds.Caleb analyzes TypeSafe AI's Jev, examining how structured probabilistic outputs and primitive types enable rapid workflow automation compared to autoregressive LLMs.
Duration: 7 minutes 11 seconds.Gary Explains breaks down TypeSafe AI's Jev model, contrasting System 1 probabilistic decision engines with conversational LLMs. He details the input state, query modes, pricing structure, and demonstrates interactive CLI requests showing sentiment analysis capabilities alongside logic and math limitations.
Duration: 10 minutes 52 seconds.Takafumi Horie explains Jev, TypeSafe AI's specialized model focused strictly on decision-making rather than text generation. He discusses its probability outputs, tiered routing systems, and practical operational implications.
Duration: 7 minutes 10 seconds.Joe Maddalone introduces TypeSafe's Jev model, explaining its typed decision primitives (choice, score, boolean). He demonstrates a TypeScript script processing video transcripts for routing and scoring before calling traditional LLMs.
Duration: 7 minutes 48 seconds.Lukas Margerie sets up a coding assistant with TypeSafe’s quickstart and remixes community demos into custom tools. The examples include a Chrome extension, a video-component workflow, and voice-driven game changes; Jev is one component of the larger toolchain.
Duration: 10 minutes 49 seconds.Matheus Battisti demonstrates Jev, TypeSafe's specialized decision model. He walks through early access, playground probabilities, and integrates Jev into a full-stack dashboard to triage incoming support messages, comparing performance side-by-side with DeepSeek Flash.
Duration: 16 minutes 3 seconds.Mau Seco introduces TypeSafe AI's Jev, explaining how it trades verbose generative chat responses for fast, structured probabilistic decision outputs. Reviewing community demonstrations—including invoice verification, Super Mario gameplay, web browsing, ad categorization, and Claude integration—he explores how Jev functions in agentic pipelines.
Duration: 4 minutes 53 seconds.This Portuguese explainer contrasts Jev’s typed decisions with sequential text generation. It examines TypeSafe’s latency and pricing claims, explains the stated RLCD training objective, and describes how application code must connect decisions into a multi-step workflow.
Duration: 7 minutes 44 seconds.Munoncode explains Jev's role as a discrete decision-making model rather than a generative chatbot. He demonstrates routing an interactive FAQ and selecting educational study missions, reviews community demos like context compaction, and assesses where Jev offers practical cost savings versus where full LLMs remain necessary.
Duration: 9 minutes 0 seconds.Ray Amjad explains TypeSafe's Jev model as a fast System 1 probability classifier. He demonstrates its three primitives—Noul, choice, and score—in the web console before exploring agentic patterns like parallel browser testing, dynamic skill selection, qualitative linting, and multi-angle PR review paired with System 2 frontier models.
Duration: 27 minutes 28 seconds.Riley Brown explains TypeSafe's Jev decision model, demonstrating its structured outputs (choice, score, Noul) and showcasing practical applications in routing and email classification.
Duration: 20 minutes 18 seconds.Sam Witteveen demonstrates TypeSafe AI's Jev model, explaining its System 1 design for rapid software decision-making across choice, score, and boolean questions. He tests classification and routing tasks, reviews claims regarding hallucination and token-free latency, and critically evaluates whether typed outputs prevent incorrect decisions.
Duration: 16 minutes 18 seconds.The creator reviews TypeSafe AI's claimed metrics for Jev, contrasts its decision design with traditional conversational LLMs, and tests the invite-only web console playground using criteria definitions and structured queries.
Duration: 15 minutes 4 seconds.This video breaks down TypeSafe AI's Jev decision model and demonstrates ten community implementations, showing how pairing generative models with dedicated fast classification transforms interactive web tools, browser automation, and context management.
Duration: 25 minutes 15 seconds.The creator backtests TypeSafe's Jev model across 300 market decisions, assessing typed outputs for trade plans, win rates, and self-contradictions.
Duration: 14 minutes 51 seconds.ThePrimeagen experiments with Jev, building a TypeScript agent loop to play Balatro by transforming raw game state into reduced prompt payloads and structuring sequential action decisions.
Duration: 148 minutes 40 seconds.
