Related reading
Efficient Estimation of Word Representations in Vector Space
This paper introduces two novel log-linear model architectures for efficiently computing continuous word vector representations from very large datasets. These models achieve state-of-the-art accuracy on syntactic and semantic word similarity tasks with significantly lower computational cost than previous neural network approaches.
Hall of Famearxiv.org27 minpaper★ Detecting spam and auto-replies with Jev and the Laravel AI SDK
Jev is a "System One" AI model focused on classification, providing calibrated probabilities for predefined answers rather than generating text. This article demonstrates its use with the Laravel AI SDK to replace complex rule-based systems for detecting spam and auto-replies in a helpdesk application.
Freek Van der Hertenfreek.dev6 minReverse-engineered Jev-like model
Jevlike is an open‑source starter model that scores a list of text options in a single forward pass. It provides a minimal architecture (option queries, shared dot‑product scorer), synthetic data generation, training/evaluation CLI, and examples on Doom and chess. The repo supports a byte‑level encoder or a frozen Hugging‑Face encoder (e.g., Qwen2.5‑0.5B), runs on CPU/MPS/CUDA, and reports benchm…
Hacker News front pagegithub.com4 minreleaseHN16224Jev introduces a new shape of LLM - System One, aka Decision Models
Jev is a new “System One” decision model that consumes text and returns numeric probabilities (yes/no, choice, score) instead of generated text, priced at $0.042 / M input tokens with free output. It’s fast, cheap, and suited for classification‑type tasks, but its opaque numeric output raises bias and explainability concerns.
Simon Willisonsimonwillison.net4 minHN5117OpenAI is well positioned to fast-follow Jev
The post argues OpenAI can quickly replicate TypeSafe’s Jev – a classifier‑style LLM that uses token‑level log‑probabilities – by training similar data and folding the capability into its own models, but notes the only real moat might be Jev’s synthetic training data and calibration process.
Hacker News front pagearcturus-labs.com12 minHN320221
