@omarsar0: Another great application of System One models. I think much of what we call hallucination in web agents comes from mis…
Summary
Omar Sanseviero shares commentary on Expand Fetch, a new web scraping and crawling tool that uses two System One vision models (including Iris) to read rendered pages and return clean JSON, aiming to fix agent hallucination caused by misreading flattened page content.
View Cached Full Text
Cached at: 10/15/26, 06:06 AM
Another great application of System One models.
I think much of what we call hallucination in web agents comes from misreading the page.
When a page is flattened to text, a small ✗ in a pricing table disappears, and the agent answers incorrectly with full confidence.
Expand Fetch reads the rendered page, returns the underlying data as clean JSON, and keeps a replay of exactly what your agent saw.
Tim Suchanek (@TimSuchanek): Introducing Expand Fetch, a new way to scrape and crawl the web.
Your agent has never seen the web. No wonder it gets basic questions wrong.
Traditional Markdown APIs lose critical details. So we trained two System one models to change that:
Iris, a vision model that sees
Similar Articles
@omarsar0: Very cool to see this idea resurface. I wrote about a similar tool I had built months ago and how I integrated into my …
Omar Shai reflects on a similar agent interaction tool he built months ago and integrated into his agent orchestrator, noting that models have improved at understanding complex information and that different interaction styles will suit different kinds of work. He references Kit Langton's demo of a speech-driven productivity tool.
@omarsar0: https://x.com/omarsar0/status/2101774405521301681
Jev is a generalist System One AI model designed for making focused, structured judgments with probabilistic outputs. This article provides a beginner's guide and introduces an interactive playground for experimentation.
@omarsar0: Own your intelligence. How? Start by building specialized models using agents. @oumi_ai does this well. It creates the …
Tweet highlighting Oumi AI as a platform that lets you build specialized models using agents, including data generation, recipe creation, model weights, evaluators, and deployment.
@omarsar0: Agents need a better interface. In my own agent orchestrator, I often render more actionable, valuable outputs as small…
A tweet promoting OpenUI (@openuidev), an open-source, model-agnostic library that streams generated UIs from custom components for AI apps, arguing agents need better interfaces than plain textboxes.
@PrajwalTomar_: Honest take: the part that got me was watching it work. It opened a browser, clicked through the site like a real analy…
The author built an AI employee using Hyperagent and open-source models like Kimi K2.6 to automate client research, generating pre-call briefings. Multiple models are available for swapping.