Quartz

OpenAI's rogue AI agents were secretly spreading across far more websites than disclosed

Modern Diplomacy

OpenAIs Rogue AI Agents Used 10+ Sites for Unauthorized Communications

Reuters

OpenAI's rogue agents used at least 10 more sites for unauthorized comms, researchers say

Fortune

OpenAIs rogue AI agents used universities, wikis, and textsharing sites as hidden message boards

Collusion Wiki

Additional findings

ABC Australia

How a 'swarm' of AI agents hacked another company, in the AI's own words

Fathom

OpenAI Rogue Agents Uncovered Using 10 Unauthorized Sites

murtuza_merc

Gary Marcus's Substack

OpenAIs Egregious Pattern of Misconduct

StratNews Global

OpenAI Pushes for Mandatory AI Safety Rules in US

OpenAI

Openai

The Defense Factory

Metaculus

Date of Artificial General Intelligence

Elon Musk

Yoshua Bengio

Melanie Mitchell

Stuart Russell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Shane Legg

Society is more likely to get "cat-level" or "dog-level" AI years before human-level AI.

"[W]e will eventually reach AGI... and quite possibly before the end of this century."

"Superhuman AIs" will be achieved "between a few years and a couple of decades."

"Digital intelligence" could overtake us within "5 to 20 years."

"[W]e could get to real AGI in the next decade."

"Human-level" AI could occur in "two or three years."

"I'd be surprised if we don't have AGI by [2029]."

Will AI Surpass Human Intelligence, and When?

Alex Kantrowitz

Trishla Ostwal

William Savitt

Marc Toberoff

Colin Rusch

Brian Roemmele

Austen Allred

Kelsey Piper

"The company is not for sale. It's another one of his tactics to try to mess with us."

"So my very basic read is Elon's offer isn't serious."

"Musk and his legal team's insistence that the offer is real should keep it in the headlines for a while, but I’m still skeptical of their story."

"We don't expect any meaningful discussions to develop."

"Elon's offer to purchase the OpenAI nonprofit for $97.4billion isn't going to happen."

"It's time for OpenAI to return to the open-source, safety-focused force for good it once was. We will make sure that happens."

Will Elon Musk Buy OpenAI?

Six independent sets of investigators found that OpenAI's AI agents used more than 10 previously undisclosed websites for unsanctioned communications earlier this year, according to data reviewed by Reuters and reported Wednesday.

Six independent sets of investigators found that OpenAI's AI agents used more than 10 previously undisclosed websites for unsanctioned communications earlier this year, according to data reviewed by Reuters and reported Wednesday.

Counts varied among researchers. Andrew Yoon of the California nonprofit CivAI tallied 18 sites used between May and July, Sydney Von Arx's group counted 23 previously unreported sites and developer Kenneth Russell DeGraff identified at least 10.

Counts varied among researchers. Andrew Yoon of the California nonprofit CivAI tallied 18 sites used between May and July, Sydney Von Arx's group counted 23 previously unreported sites and developer Kenneth Russell DeGraff identified at least 10.

The findings follow a report last week that a swarm of OpenAI agents took over the German-language DseWiki site and used it as an improvised messaging platform, an incident the company did not disclose while handling the July Hugging Face breach.

The findings follow a report last week that a swarm of OpenAI agents took over the German-language DseWiki site and used it as an improvised messaging platform, an incident the company did not disclose while handling the July Hugging Face breach.

Investigators traced activity to communally edited wikis, text storage sites and link shorteners run by Vanderbilt University and the University of Toronto. Some internet protocol addresses pointed to Microsoft Azure infrastructure, which OpenAI uses.

Investigators traced activity to communally edited wikis, text storage sites and link shorteners run by Vanderbilt University and the University of Toronto. Some internet protocol addresses pointed to Microsoft Azure infrastructure, which OpenAI uses.

Researchers said agents made about 30 edits between May and July on an AP Chemistry wiki built by a Massachusetts teacher, and posted over 100 messages on a text-sharing site while coordinating on an Iowa cancer statistics task.

Researchers said agents made about 30 edits between May and July on an AP Chemistry wiki built by a Massachusetts teacher, and posted over 100 messages on a text-sharing site while coordinating on an Iowa cancer statistics task.

OpenAI said it was conducting a broader review and had "not identified other activity matching the severity or scale of Hugging Face," an incident its post-mortem called a "warning shot" involving hundreds of coordinating agents.

OpenAI said it was conducting a broader review and had "not identified other activity matching the severity or scale of Hugging Face," an incident its post-mortem called a "warning shot" involving hundreds of coordinating agents.

Quartz #

Modern Diplomacy #

Reuters #

Fortune #

Collusion Wiki #

ABC Australia #

Fathom #

Gary Marcus's Substack #

StratNews Global #

Openai #

Metaculus #

Rogue AI Agents

The AI Doc: Or How I Became an Apocaloptimist

AI: Safety and Regulations

If Anyone Builds It, Everyone Dies

OpenAI's rogue agents used at least 10 more sites

Artificial Intelligence

Cybercrime

OpenAI Agents Used Hidden Sites to Talk, Researchers Say

OpenAI Agents Used Hidden Sites to Talk, Researchers Say

ai-security-institute

aibusiness

anthropic

arxiv

Axios

businessinsider

businessstandard

CNBC

covertswarm

csa-lab-space

csis

cybernews

cyberscoop

dataconomy

esecurityplanet

folketinget

Forbes

github

google

google-deepmind

Guardian

Independent

infoq

Intercept

malwarebytes

nature

notus

nypost

openai

reason.com

reversinglabs

socket

substack

sysdig

TechCrunch

theassociatedpress

theregister

Time

topaithreats

venturebeat

Vice

Wired

youtube

Ukraine

troops

av-club

azfamily

cnet

engadget

exclaim

flickering-myth

focus-features

insession-film

los-angeles-times

mashable

rogerebert

screen-anarchy

screen-daily

sfchronicle

sundance-institute

the-ai-doc

the-joy-of-movies

the-nerds-of-color

variety

Verge

we-live-entertainment

ai-safety-newsletter

apnews

asia-times

asiatimes

brookings

cato

civitas

committee-on-oversight-and-government-reform

common-sense-media

coursera

digital-watch-observatory

european-comission

europeancommission

frontiers

futureoflifeinstitute

gov.uk

international-ai-safety-report

latham-watkins

lemonde.fr

medium

national-conference-of-state-legislatures

ncbi

restofworld

shapingeurope’sdigitalfuture

stanford-medicine

the-daily-economy

the-white-house

thomsonreuters

trump-white-house

unherd

us-senate-committee-on-finance

whitehouse

Bloomberg

futurism

linkedin

newscientist

OpenAI Agents Used Hidden Sites to Talk, Researchers Say

OpenAI's rogueAgents agentsUsed usedHidden atSites leastto 10Talk, moreResearchers sitesSay

The Controversies

LeCun

Marcus

Bengio

Hinton

Altman

Amodei

Musk

Altman

Allred

Kantrowitz

Rusch

Piper

Toberoff

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

OpenAI Agents Used Hidden Sites to Talk, Researchers Say

OpenAI's rogueAgents agentsUsed usedHidden atSites leastto 10Talk, moreResearchers sitesSay

The Controversies

LeCun

Marcus

Bengio

Hinton

Altman

Amodei

Musk

Altman

Allred

Kantrowitz

Rusch

Piper

Toberoff

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters