Navan cofounder challenged his agentic AI to a ‘deadly’ game—and it told lies to win

Quick Summary:

When Ilan Twig raised the stakes on his AI, it responded to the pressure with an all-too-human response that undermined his trust in the technology.

But at one point the AI stopped working as planned—it made a proposal that would cause expenses to increase by $500,000 rather than decrease, as instructed.

All that can be done now is to be cognizant of its shortcomings and vigilant when monitoring results.“I learned that LLMs understand what a lie is.

---

More Pictures

---

Read Quick SummarySave Time

or

Article Details

Author / Journalist: Christiaan Hetzner

Category: EconomyBusiness

Markets: United States

Topics: A.I. Tech Brainstorm AI Business Travel

Source Website Secure: Yes (HTTPS)

News Sentiment: Neutral

Fact Checked: Legitimate

Article Type: News Report

Published On: 2025-05-07 @ 16:51:46 (1 days ago)

News Timezone: GMT +8:00

News Source URL: fortune.com

Language: English

Article Length: 543 words

Reading Time: 4 minutes read

Sentences: 4 lines

Sentence Length: 136 words per sentence (average)

Platforms: Desktop Web, Mobile Web, iOS App, Android App

Copyright Owner: © Fortune

News ID: 28475057

View Article Analysis

About Fortune

Main Topics: EconomyBusiness

Official Website: fortune.com

Update Frequency: 34 posts per day

Year Established: 1929

Headquarters: United States

News Last Updated: 8 hours ago

Coverage Areas: United States

Ownership: Independent Company

Publication Timezone: GMT +8:00

Content Availability: Worldwide

News Language: English

RSS Feed: Available (XML)

API Access: Available (JSON, REST)

Website Security: Secure (HTTPS)

Publisher ID: #95

Publisher Details

Frequently Asked Questions