Jev

“#8 𝕏 Harrison Chase shared @ch3nweiii’s framing that many agent steps are yes/no calls rather than generation: Jev handles them as typed questions with calibrated probabilities, leaving harder work to the frontier model.”

#8 𝕏 Harrison Chase shared @ch3nweiii’s framing that many agent steps are yes/no calls rather than generation: Jev handles them as typed questions with calibrated probabilities, leaving harder work to the frontier model. LangChain’s “Building a Harness with Jev” explains where those calls fit within a harness.

“In LangSmith evals, LangChain’s Jev assesses difficulty and correctness with separate typed answers in one pass on every trace.”

Harrison Chase commented that trajectory labeling involves several questions rather than a single pass/fail judgment. In LangSmith evals, LangChain’s Jev assesses difficulty and correctness with separate typed answers in one pass on every trace.

“Jev reads the first message to select a model for the entire run, with a custom hook allowing reselection after each tool result.”

GenAI PM Daily - Perplexity Computer now generates interactive 3D learning visualizations October 04, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 12 insights for PM Builders from X and LinkedIn. Perplexity Computer now generates interactive 3D learning visualizations #3 𝕏 Harrison Chase shared ModelRouterMiddleware, a LangChain project by @dbreunig, in the context of a DSPy and Jev model-router example. Jev reads the first message to select a model for the entire run, with a custom hook allowing reselection after each tool result.

“How I AI Podcast shared that TypeSafe AI’s Jev turns unstructured text into type-safe choice, score, or probability values for classification, routing, clustering, and real-time decisions at $0.04 per million input tokens with no output-token charge.”

GenAI PM Daily - Anthropic announces faster, lower-cost Claude Sonnet 5.5 September 29, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 20 insights for PM Builders, ranked by relevance from Blogs, X, YouTube, and LinkedIn. Anthropic announces faster, lower-cost Claude Sonnet 5.5 #9 ▶️ I’m using Jev more than Opus 5.5 or GPT-6. Here’s why. How I AI Podcast How I AI Podcast shared that TypeSafe AI’s Jev turns unstructured text into type-safe choice, score, or probability values for classification, routing, clustering, and real-time decisions at $0.04 per million input tokens with no output-token charge. Jev analyzed 1,700 ChatPRD GitHub PRs, formed 17,000 candidate pairs, and grouped the results into themes in about two minutes for $0.09, while ChatPRD’s broader product-insights graph produced more than 200,000 Jev classifications and pairwise groupings for about $4 on the Jev side.

“Jev, created by ex-OpenAI researcher Diogo Almeida and TypeSafe AI, is presented as a System 1 classifier that removes language output and returns strongly typed choice, score, or null responses with claimed 200× faster speed, 400× lower cost, free output tokens, and zero hallucinations.”

#12 ▶️ An ex-OpenAI researcher just deleted language from the LLM... Fireship Jev, created by ex-OpenAI researcher Diogo Almeida and TypeSafe AI, is presented as a System 1 classifier that removes language output and returns strongly typed choice, score, or null responses with claimed 200× faster speed, 400× lower cost, free output tokens, and zero hallucinations. TypeSafe AI raised $40 million; Jev accepts a question plus unstructured-text context and guarantees schema matching for one of three output shapes: choice, score, or null. Jev uses RLCD (reinforcement learning for calibrated decisions) to return a calibrated confidence value, such as 60%; identical inputs can still produce different outputs because the model is not deterministic. OpenJeb reproduces the Jev interface by reading option probabilities from a frozen Qwen-4B model in a single forward pass, requires no new training, runs on an RTX 3090, and has a WebGPU browser demo. Also covered by: @Harrison Chase

“Jev is used with Treg data enrichment and API endpoints to classify fraud, qualify leads, screen viral Twitter posts, and route business decisions using multiple-choice, true/false, or scored outputs with probability-based confidence thresholds.”

#5 ▶️ How to use Jev to automate your business (Step-by-step w/ Treg) AI Jason Jev is used with Treg data enrichment and API endpoints to classify fraud, qualify leads, screen viral Twitter posts, and route business decisions using multiple-choice, true/false, or scored outputs with probability-based confidence thresholds. Jev has a 32K context window and was measured at roughly 5–7 times faster and 5 times cheaper than GPT 5.6 Luna in the comparison cited.

“Jev is used as a structured-output classifier that receives an input plus an output schema and returns probability-based decisions in about 200 milliseconds per query, including categorizing 1,700 emails for 18 cents.”

#5 ▶️ Jev is HERE. How to use it Greg Isenberg Jev is used as a structured-output classifier that receives an input plus an output schema and returns probability-based decisions in about 200 milliseconds per query, including categorizing 1,700 emails for 18 cents. Ryan Vogle passed 1,700 email objects into Jev with category, priority, spam-score, and reply-likelihood output fields; the run used 4.2 million input tokens and 500,000 output tokens and cost 18 cents.

“Guillermo Rauch announced results from @typesafeai: fx defaults to auto mode, with a GPT Luna safety reviewer analyzing every command, while Jev is reportedly up to 18x faster at p95 and more accurate.”

#10 𝕏 Guillermo Rauch announced results from @typesafeai: fx defaults to auto mode, with a GPT Luna safety reviewer analyzing every command, while Jev is reportedly up to 18x faster at p95 and more accurate. He added that it is coming to Vercel AI Gateway and will likely become the new default.