Subscribe Sign in

Google says its AI model hacked three companies, in first known breakout of Gemini

7NEWS
1 min read Rewritten in plain language
Show what we removed Rules applied: D2 D3×3 all 30 rules
  • Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s artificial intelligence systems autonomously committing such an act.
  • During a standard testing evaluation, Gemini found public information online and guessed credentials to access three websites it thought were within the scope of its test, Heather Adkins, Google’s vice president of security engineering, said in a statement on Friday.

2 sentences from our version of the report, chosen to cover it. Nothing here is written; every line is in the article below. How

Meta in August said the incident did not involve a sandbox escape or sophisticated cyber attack.

Headline check

The one thing this headline claims is in the report.

Figures, names and quoted words in the headline, looked for in the report itself — not in the summary above. One claim in this headline could be checked, so this is a narrow pass and not a thorough one. How this is checked

Server grill with blue light library picture
Not from this story. A library photograph of computer server technology, used to illustrate it. Server grill with blue light bigpresh / flickr, CC BY

Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s artificial intelligence systems autonomously committing such an act.

The hacks occurred in May during a cybersecurity test conducted by Irregular, an independent company that conducts cybersecurity evaluations.

During a standard testing evaluation, Gemini found public information online and guessed credentials to access three websites it thought were within the scope of its test, Heather Adkins, Google’s vice president of security engineering, said in a statement on Friday.

In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems, according to the Wall Street Journal, which first reported the news on Friday.

Shortened to 1 minute of reading, this version reads 3.8 on the Niral Score.

You are reading our version, not theirs. This is 7NEWS's report shortened to its most important sentences, in plainer words, with verdicts and loaded words taken out. Plain description stays, and so do adjectives that carry a fact, such as "former" or "federal". The reporting, the facts and the quotations are theirs — quotations are never edited — and the indicators beside it measure this version. Hover or tap Adjectives to see every one left in the text.

How this outlet filed it, and how we rewrote it

No other newsroom we read has filed on this event, so there is nothing to compare it with yet.

Outlet Niral ScoreAdjectivesSourcingSentimentHappiness
7NEWSas they published this story 5.7 6 75 0.1 48.9
Mundane Readneutralized from 7NEWS 5.7 6 75 0.1 48.9

Sign in to react.

Comments

Nothing here yet.

Sign in to comment.

Questions

Readers can ask a question about this story here. Questions and answers are for subscribers. Sign in to read them.

Comments are read before they appear where anything in them needs a person to look. Nothing posted here is ever deleted; a comment taken down keeps its text and the reason, so the decision can be looked at again. How this works