Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Patrick Jiang Profile picture
Patrick Jiang
@patpcj
CS PhD @ UIUC @siebelschool, Research Fellow @AnthropicAI; prev: SR @GoogleResearch; recent work: DeepRetrieval, s3, R4T, Context-1, Harness-1 (w/ @trychroma)
Jun 6 • 14 tweets • 5 min read
Introducing Harness-1, a 20B search agent trained with a state-externalizing harness.

> frontier-level long-horizon search, rivaling Opus-4.6 and outperforming GPT-5.4

> Context-1-level cost and latency

> externalizes candidates, evidence, verification, and search history

> open-source [1/N] I’ve been wondering:

maybe search agents are bad at search partly because we make them do all the paperwork in their head.

So I tried a simple idea:

externalize the search state, then train the model to use that harness.

The result is Harness-1: a 20B search agent that can match or even beat much larger frontier AI on hard long-horizon search tasks.Image