#Jev (10)

Waterfall Pagination

0:22

Harness² drives JEV 1.14: frozen weights, self-evolving prompts, tools and lessons

@openmys · 198 views · 2026-10-19

Agent HarnessRecursive self-improvement

0:59

Jev Adds Real-Time Video Understanding

@ErenAILab · 141 views · 2026-10-16

JevRealtime Video

Jev 1.14 adds image bounding box generation, now served through the TypeLLM API

@TypeLLM · 158 views · 2026-10-15

JevTypeLLM

0:23

Nav Arena "Can Jev Nav?": 133 environments and 2,000+ tasks benchmark System-1 language models driving robots; a WorldState rewrite lifts Jev from 40% to 90%

@stash_pomichter · 760 views · 2026-09-30

NavigationBenchmarks

Building an Agentic Harness with Jev: A Builder's Guide

Avid's 3,500-word build log: Jev as a decision layer inside keel, a local-first Rust coding workspace. One principle carries it: a model can suggest the next move, the host still owns the move — the host prepares the menu, Jev picks from it, the host checks again; pinned routes and live sessions bypass automatic selection; selection grants no permission. Plus how decision receipts become replayable evaluation scenarios.

BLOG

Agentic HarnessJev

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures

RLCDAlignBench spans 44 benchmarks and 7,193 instances. One generic question reaches median AUROC 0.886; soft probabilities beat argmax.

Ruoqi Guo, Yi Liu, Gelei Deng · 1.3k views · Sep 24, 2026

AI AlignmentAlignment Failure Detection

Sep 24, 2026

0:39

PiPER recovers after moving-target tests

@huxiao93612565 · 620 views · 2026-09-21

Embodied AIRobot Manipulation

Build Your Own Jev (100% Local): Recreating Fixed-Answer Scoring with SGLang

Jev-style fixed-answer scoring reproduced locally with SGLang /v1/score: single-token labels, restricted softmax, confidence-gated routing, and a 6 ms vs 1088 ms benchmark against generation.

BLOG

JevSystem One Models

0:59

Jev vs GPT-6 Astra vs GPT-4.1 mini: one apple-plate task, three LLM controllers in MuJoCo

@openroboto · 895 views · 2026-09-19

LLM ControlManipulation

Jev and System One Models: Frontier Intelligence as a Function Call

A deep read of TypeSafe's first System One Model: three question primitives, the economics of parallel calls, confidence-gated routing, eval caveats, eight jagged edges, and the OpenJev local repro.

BLOG

TypeSafeJev

As an Amazon Associate, we earn from qualifying purchases.