---
format: "aidr-story-markdown/v1"
id: "7f5c627298368a7eb8db5d2f863eec792dc6c6f632f4fb66badcb6973008bfba"
canonical_url: "https://aidr.today/7f5c6272?lang=en"
title: "Building trustworthy AI by fencing it in, not predicting it"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-16T16:04:28.000Z"
category: "Research"
topics: ["safety"]
source_urls: ["https://www.technologyreview.com/2026/11/16/1148565/building-trustworthy-ai-by-fencing-it-in-not-predicting-it/"]
summary: "Building trustworthy AI requires making it bounded, observable, and controllable rather than attempting to predict it."
---

# Building trustworthy AI by fencing it in, not predicting it

> [Open the canonical story](<https://aidr.today/7f5c6272?lang=en>)

**Published:** 2026-11-16T16:04:28.000Z
**Category:** Research
**Topics:** safety

## Summary

Building trustworthy AI requires making it bounded, observable, and controllable rather than attempting to predict it\.

## Sources

- [Story source](<https://www.technologyreview.com/2026/11/16/1148565/building-trustworthy-ai-by-fencing-it-in-not-predicting-it/>)

