@fdellaert

Article

Could Jev + graphical models fundamentally change how we build systems that reason under uncertainty? Unless you've been off the grid this week, you now know that <a target="_blank" href="https://typesafe.ai/blog/introducing-system-one-models-and-jev" color="blue">Jev</a> is @typesafeai’s new model ...

@winarakniyeol

Thread

Magiging ninong si Jongdae ng panganay ni Sehun at Irene. Pero pano naman ang panganay ni Sehun at Jongdae na nabuo sa isang pagkakamali? ...

@winarakniyeol

Thread

[Sechen] Hacienda Kim is losing its gloriousness because of the Oh's only son's revenge. Jongdae, the third child bravely makes a move by coming into the Oh turf. "Tigilan mo na ang pamilya ko." "And what will I get in return?" "I'll marry you and let me receive your wrath." ...

@predict_addict

Thread

Update: as some folks have commented it appears to be “calibrated” with a version of Platt’s scaler aka temperature scaling. If true it is a rather dumb idea considering that: 1) Platt’s scaler was invented specifically for support vector machines assuming specific shape of class scores. 2) rel...

@neural_avb

Thread

JEV actually doesn't even run deterministically Exact same prompts give you different probabilities when you run it multiple times The ORDER of the choices DRASTICALLY changes the output probs I am more and more confused by the their "no-hallucination" claim <span class="quote-card" data-quote-i...

@simplifyinAI

Article

> Every agent runs into the same problem. A model that costs $0.03 per call spends its time answering yes-or-no questions, picking the next worker, or scoring relevance. None of that needs generation. It needs a model built specifically to decide....

@JoshARosen

Article

Jev has been out for less than a week, but we’re already starting to see patterns in how people are building with it. And they are all over the place....

@_avichawla

Article

Everything you need to turn an open-source LLM into a fast, local decision engine without retraining it. It covers next-token scoring, fixed choices with probability distributions, SGLang, and a hands-on benchmark against standard text generation on the same model....

@PetraGuasti

Thread

1/16 After the elections in Berlin and Mecklenburg-Vorpommern, we will hear a lot about “the extremes”: Die Linke winning in Berlin and the AfD in MV. But the radical left and the extreme right are not mirror images. And treating them as such obscures more than it explains. ...