42 stories
Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores. As these models are increasingly used for automated decision-making, understanding their reliability under adversarial manipulation becomes critical.
Is this the JEV killer? The post A Practical Guide to OpenAI's New Decisions API appeared first on Towards Data Science.
TypeSafe Inc., the creator of the Jev artificial intelligence model, today announced that it has raised $870 million in funding at a $7.5 billion valuation. Andreessen Horowitz led the round with contributions from Sequoia Capital, DCVC and unnamed angel investors.
How a decision-first model can catch risky tool calls before they turn into real-world actions The post Can TypeSafe's Jev Make AI Agents Safer Without Another LLM? appeared first on Towards Data Science.
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I had GPT-6 Astra read the new OpenAI API documentation and build an llm-openai-decisions plugin…
Model routing can finally be a design choice rather than a system enhancement The post How to Build a Cheap, Yet Reliable Model Router With Jev appeared first on Towards Data Science.
fast-jev-compaction prunes in a second, not 30. At its default threshold it keeps almost no tool results, and a scorer that always says no cuts as much.
The flagship model of modern deterministic-probabilistic decision engines does not write you a paragraph. It does not tell you a story, apologize for its limitations, or generate a list of caveats. It answers a typed question and hands you back a number.
You can get Jev-style typed decisions from an ordinary LLM by forcing one output token and reading its logprobs. Where that matches Jev, and where it loses.
Originally published on the WebSpeaker blog. In short: We tested Jev, a new model for rapid decisions, as a way to speed up WebSpeaker. Jev made decisions quickly and slightly more accurately than the model we use today. Yet in every variant we tested, visitors waited longer for an answer.
Sure, it costs more, but it can handle images and video and it's available on Hugging Face if you have the hardware horsepower to run it locally
Amazon Web Services Inc.’s Strands Labs team has been playing around with an emerging class of lightweight artificial intelligence systems known as “decision models,” and it’s now making the fruits of that work available to the open-source community.
Suppose you’re building a service that receives customer support tickets. Before assigning a ticket, your code needs to answer two questions: Which team should handle it? Does it need urgent attention? You could ask a language model to write an assessment and then parse its response.
We shipped TypeSafe's Jev into our AI employee's memory five days after launch: measured latency, how we set a 0.7 threshold, where Jev fails, and what it costs.
Jevstiller targets 98% agreement by learning familiar requests on your hardware while sending uncertain and audited queries upstream
Jev is a new AI that is making news and it doesn't chat. You can use it do small classification tasks. In this video, we take one real support ticket from a customer named Alan and follow it all the way through: what we send Jev, what comes back, and how the program decides what to do with the…
Not every decision needs a decoder, generation Is not always a decision The post When All You Have Are Decoders, Every Decision Looks Like Generation appeared first on Towards Data Science.
Pydantic AI can run an agent on TypeSafe's Jev, a model that answers typed questions instead of writing text. Pydantic Logfire now shows each question, answer, and probability in Live view.
Showing 18 of 42 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
