OpenAI Threatens Bans as Users Probe Its ‘Strawberry’ AI Models

Quick Summary:

Nothing is more enticing to enthusiasts than information obscured, so the race has been on among hackers and red-teamers to try to uncover o1's raw chain of thought using jailbreaking or prompt injection techniques that attempt to trick the model into spilling its secrets.

One X user reported (confirmed by others, including Scale AI prompt engineer Riley Goodside) that they received a warning email if they used the term "reasoning trace" in conversation with o1.

Exposing o1's raw chain of thought would be a bonanza of training data for competitors to train o1-like "reasoning" models upon.

---

More Pictures

---

Read Quick SummarySave Time

or

Article Details

Author / Journalist: Benj Edwards, Ars Technica

Category: TechnologyEconomy

Markets: United States

Topics: Research Artificial intelligence Disable comments Splitscreenimagerightfullbleed Openai External_partner Ars technica

Source Website Secure: Yes (HTTPS)

News Sentiment: Negative

Fact Checked: Legitimate

Article Type: News Report

Published On: 2024-09-17 @ 23:00:00 (11 hours ago)

News Timezone: GMT +8:00

News Source URL: wired.com

Language: English

Article Length: 1236 words

Reading Time: 7 minutes read

Sentences: 41 lines

Sentence Length: 31 words per sentence (average)

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

Copyright Owner: © Wired

News ID: 22571815

View Article Analysis

About Wired

Main Topics: TechnologyEconomy

Official Website: wired.com

Update Frequency: 11 posts per day

Year Established: 1993

Headquarters: United States

News Last Updated: 14 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: #111

Publisher Details

Frequently Asked Questions