Hello Demo,
Not every AI task needs a model to think hard and write an essay. Sometimes, you just need it to make a call: Is this customer complaining, asking for a refund, or trying to buy something?
That seemingly boring job helps explain why developers have been buzzing about a new model called Jev over the past two weeks. Vercel, a popular cloud platform for developers, says Jev became its fastest-adopted model based on the number of paying teams who used it within the first 24 hours of its release.
So what’s all the hype about?
Jev is built to make decisions, an approach shaped by its creator and TypeSafe founder, Diogo Almeida, who helped build ChatGPT at OpenAI.
Provide some information, ask a question, give a set of possible solutions, and it picks an answer for you. It even assigns probabilities to the options provided.
Some billionaires famously wear the same outfit every day for a reason: Fewer choices mean fewer decisions. With Jev, instead of asking a model to generate from a near-limitless universe of possible answers, you narrow the field and ask it to choose.
Large language models (LLMs) can do this, too, but they are built to generate answers token by token, which can be an overkill when all you need is a quick pick among several options.
To be clear, Jev isn’t trying to replace LLMs. It can decide which tool to use or what action to take next, unlike an LLM, which steps in when the job requires deeper reasoning.
 Image credit: Made by Ulla/Tech in Asia with the help of AI Some companies are already finding uses for Jev.
Ivan Lee, founder and CEO of Datasaur, says his team has been experimenting with the model for the company’s annotation platform. He describes Jev as a “universal classifier” that offers an alternative to both LLMs and traditional classification models.
LLM inference costs can quickly add up when labeling data at scale, according to Lee. And while traditional classification models are cheaper, they require additional training for each new task.
Others are already seeing those savings in practice.
Leonard Loo, co-founder and CEO of Voltade, says his AI agent startup has deployed Jev to filter and label customer messages.
Filtering 700 customer messages used to take five minutes with DeepSeek Flash. But with Jev, the same process now takes 20 seconds and costs 200x less, Loo wrote on LinkedIn. The feature is already live for Voltade’s users.
Kevin Daniel Pantasdo, founder of AI coding startup Superalignment, estimates that categorizing 100,000 financial transactions costs about US$60 with Claude Haiku 4.5 but only US$2 using Jev. He acknowledges that the actual cost of using Claude can be cheaper when factoring in caching and batch discounts, but using Jev is still cheaper.
OK, Jev is indeed useful. But is it revolutionary? On X, one developer questioned the excitement around use cases that traditional classifiers can already handle.
Then there are the imitators. Within days, open-source alternatives to Jev had popped up on GitHub and Hugging Face. Inference startup Together AI also published a guide to training a Jev-like classifier for US$17.
Lee of Datasaur is curious about the quick arrival of competitors.
“If this is relatively simple to recreate from an LLM, what occupied TypeSafe’s two years in stealth?” he asks.
Still, Jev’s creator, TypeSafe AI, is looking like the hot new kid on the block. The Financial Times reported that the startup could be raising a massive new round at a US$10 billion valuation or more.
Meanwhile, here are some of our recent AI stories that are worth checking out:
Glenn Kaonang, journalist
Catch up on past issues of the newsletter here.
|
