Shown·Failed, with a lesson·Operator
Operator concert and product research
Operator, OpenAI's browser agent, was tried on finding Berlin classical concerts and researching Anki competitors, using prompts and screen recordings.
Both tasks failed. The concert search returned three wrong concerts after 33 minutes, and the Anki competitor list had incorrect data.
Overview
How it was set up
OpenAI Operator, a ChatGPT agent with its own VM and browser. The author wrote prompts, once drafted with GPT-4, and could not log in to accounts.
Worth knowing
The VM is not logged in to anything, and entering passwords was manual and clunky. The author calls it a research preview.
A prompt to start from
The source does not show the prompt.
Sources 1
History
- Source published
- 2025-01-29
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/operator-concert-and-product-research.md
More in research
36 featsResultIt created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
ResultOperator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
ResultThe draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.