Rl-Training · AI Beat

20 Sep 2026 · AI Beat Desk

Before Jev, There Was Laya

Four days after TypeSafe AI launched Jev as a breakthrough "System One" decision model, a developer surfaced an open-source project called Laya built on the same principle a year earlier — faster, more accurate, and fully public. The 1,170-point Hacker News thread that followed is less about credit disputes and more about what happens when a frontier lab takes an existing idea, applies prestige and marketing, and erases the prior art.

17 Sep 2026 · AI Beat Desk

Teaching a 4B Model to Outplan Postgres

Rohan Bansal trained a 4B parameter model to generate Postgres join-order hints via distillation from a frontier model followed by reinforcement learning with a custom anchored GRPO variant — yielding a 1.81× geometric mean speedup on 113 join-heavy queries for about $1,200 in total compute. The methodology shows how cheap specialist RL is getting for niche performance optimization tasks.

16 Sep 2026 · AI Beat Desk

Jev Doesn't Generate Text, and That's the Point

TypeSafe AI shipped Jev, a "System One" model that deliberately abandons text generation in favor of parallel typed probabilistic decisions. By giving up string output entirely, it sidesteps hallucination, cuts latency to under 500ms, and costs two orders of magnitude less than frontier LLMs on structured automation tasks — a deliberate specialization rather than another attempt to scale up a general model.