---
id: "nr-jerry-liu-frames-jev-alongside-model-routing-and-post-31dbe7"
slug: "jerry-liu-frames-jev-alongside-model-routing-and-post-31dbe7"
title: "Jerry Liu frames Jev alongside model routing and post-training"
observed_at: "2026-09-18T13:48:49+00:00"
record_date: "2026-09-18"
date_kind: "observed_at"
novelty: "new"
source_platform: "x.com"
topics: ["model-routing","post-training","model-architecture"]
entities: ["Jev"]
related_patterns: []
source_url: "https://x.com/jerryjliu0/status/2100777020330491984"
source_urls: ["https://x.com/jerryjliu0/status/2100777020330491984"]
basket: {"id":"0325e6b8-f527-4f9b-bfa3-3f30e57f380b","revision":1,"cluster_id":"31dbe7e9-00cb-4a1f-aac6-fdba3dfb3350"}
type: "raw_signal"
description: "Jerry Liu argues that Jev, routing, and post-training are three ways to optimize accuracy, cost, and latency for specific tasks."
why_it_matters: "For engineers, the framing separates three levers: harness, weights, and architecture, each trading accuracy, cost, and latency differently. The post is an opinion and does not provide measurements comparing the three approaches on any task."
verification_level: "source-inspected"
signal_type: "newsroom_basket_signal"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:jerry-liu-frames-jev-alongside-model-routing-and-post-31dbe7"
retrieval_nugget: "Jerry Liu argues that Jev, routing, and post-training are three ways to optimize accuracy, cost, and latency for specific tasks. Jerry Liu published a post placing Jev next to model routing and post-training as ways to optimize intelligence for a specific task. In his framing, routing orchestrates frontier and open-weight models at the harness layer, post-training tunes an existing model"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/jerry-liu-frames-jev-alongside-model-routing-and-post-31dbe7/","markdown":"https://newruntime.com/signals/jerry-liu-frames-jev-alongside-model-routing-and-post-31dbe7.md","json":"https://newruntime.com/signals/jerry-liu-frames-jev-alongside-model-routing-and-post-31dbe7.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Jerry Liu frames Jev alongside model routing and post-training

## Retrieval answer

Jerry Liu argues that Jev, routing, and post-training are three ways to optimize accuracy, cost, and latency for specific tasks. Jerry Liu published a post placing Jev next to model routing and post-training as ways to optimize intelligence for a specific task. In his framing, routing orchestrates frontier and open-weight models at the harness layer, post-training tunes an existing model

Jerry Liu published a post placing Jev next to model routing and post-training as ways to optimize intelligence for a specific task. In his framing, routing orchestrates frontier and open-weight models at the harness layer, post-training tunes an existing model toward task evals, and Jev introduces a new architecture for generalized classification.

For engineers, the framing separates three levers: harness, weights, and architecture, each trading accuracy, cost, and latency differently. The post is an opinion and does not provide measurements comparing the three approaches on any task.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Model Routing](https://newruntime.com/topics/model-routing.md): Explore the model-routing topic hub.
- topic hub: [Post Training](https://newruntime.com/topics/post-training.md): Explore the post-training topic hub.
- topic hub: [Model Architecture](https://newruntime.com/topics/model-architecture.md): Explore the model-architecture topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)