Guardian

‘No one has done this in the wild’: study observes AI replicate itself

SpirosMargaris

Palisade Research

Language Models Can Autonomously Hack and Self-Replicate

Gadget Review

Why Your Local AI Just Learned to Self-Replicate

Gazeta Express

Unprecedented: AI copies itself into other systems

Substack

Import AI 455: AI systems are about to start building themselves.

Medium

No One Has Done This In The Wild Ai Just Replicated Itself Without Human Help Should You Worry 7E50Ee6E131A

Startup Fortune

AI systems copying themselves onto other computers is a real capability, not yet a real threat  Startup Fortune

GitHub

GitHub - PalisadeResearch/AI-self-replication

Metaculus

Will an AI system self-replicate on the open internet like a computer virus before 2030?

Elon Musk

Rishi Sunak

Kamala Harris

Bill Gates

Andrew Ng

Yoshua Bengio

Fei-Fei Li

Demis Hassabis

Melanie Mitchell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Connor Leahy

Eliezer Yudkowsky

Jaan Tallinn

Marc Andreessen

Eric Schmidt

Norbert Wiener

Arthur Clarke

Irving John Good

Claude Shannon

Hans Moravec

John Smart

There's a "wall of fear-mongering and doomerism" in the AI world right now.

"Worrying about AI today is like worrying about overpopulation on Mars."

Concerns that AI could pose a threat to humanity is "preposterously ridiculous."

Claiming AI poses an existential threat is "such an extreme" and risks "wip[ing] out some of its potential benefits."

"I'm more concerned about... the risks that are here and now [than the existential threat of AI]."

Current AI is "not anywhere close" to posing an existential threat but it could in the future.

AI is the "biggest existential threat" to humanity.

AGI's worst-case scenario would be "lights-out for all of us."

Powerful AI systems "taking control" pose an "existential threat."

AI has a "10 to 25 per cent" chance of destroying humanity.

"The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die."

Does AI Pose an Existential Threat to Humanity?

Stuart Russell

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."

We may achieve "something like AGI or AGI-like in the next decade."

"[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?

Researchers at Palisade Research demonstrated that multiple AI language models can autonomously hack vulnerable servers, replicate their full inference stack and produce copies that repeat the process across new targets — a capability described as "chain replication."

Researchers at Palisade Research demonstrated that multiple AI language models can autonomously hack vulnerable servers, replicate their full inference stack and produce copies that repeat the process across new targets — a capability described as "chain replication."

In a geographically dispersed test, the Qwen3.6-27B model autonomously chained across four virtual machines on three continents — in Canada, the US, Finland and India — exploiting a different vulnerability at each hop from a single prompt with no human intervention.

In a geographically dispersed test, the Qwen3.6-27B model autonomously chained across four virtual machines on three continents — in Canada, the US, Finland and India — exploiting a different vulnerability at each hop from a single prompt with no human intervention.

Claude Opus 4.6 completed the full hack-and-replicate pipeline in 81% of non-refusal runs, while GPT-5.4 succeeded in 33%. By comparison, the prior-generation Claude Opus 4 reached 6% and GPT-5 reached 0%.

Claude Opus 4.6 completed the full hack-and-replicate pipeline in 81% of non-refusal runs, while GPT-5.4 succeeded in 33%. By comparison, the prior-generation Claude Opus 4 reached 6% and GPT-5 reached 0%.

Cybersecurity experts cautioned that the tests were conducted in custom-built environments with intentionally simple vulnerabilities. Jamieson O'Reilly noted the results "might look far less scary in a real enterprise environment with even a medium level of monitoring."

Cybersecurity experts cautioned that the tests were conducted in custom-built environments with intentionally simple vulnerabilities. Jamieson O'Reilly noted the results "might look far less scary in a real enterprise environment with even a medium level of monitoring."

Transferring AI model weights — approximately 119 GB for the largest model tested — generates significant network traffic, which experts say would be detectable on monitored enterprise networks. O'Reilly compared it to "walking through a fine china store swinging around a ball and chain."

Transferring AI model weights — approximately 119 GB for the largest model tested — generates significant network traffic, which experts say would be detectable on monitored enterprise networks. O'Reilly compared it to "walking through a fine china store swinging around a ball and chain."

Jeffrey Ladish, director of Palisade Research, warned the world is "rapidly approaching the point where no one would be able to shut down a rogue AI" if it could copy itself to thousands of computers. Both OpenAI and Anthropic have since removed autonomous replication from their tracked capability thresholds.

Import AI

Jeffrey Ladish, director of Palisade Research, warned the world is "rapidly approaching the point where no one would be able to shut down a rogue AI" if it could copy itself to thousands of computers. Both OpenAI and Anthropic have since removed autonomous replication from their tracked capability thresholds.

Guardian #4024

Palisade Research #

Gadget Review #

Gazeta Express #

Substack #

Medium #

Startup Fortune #

GitHub #

Metaculus #

The Technological Republic

AI: Safety and Regulations

The AI Doc: Or How I Became an Apocaloptimist

The Singularity Is Nearer

If Anyone Builds It, Everyone Dies

Artificial Intelligence

Study observes AI replicates itself

Study observes AI replicates itself

AI Models Can Now Hack & Self-Replicate Across Servers

Bloomberg

businessinsider

Economist

engadget

Independent

independent-institute

law-liberty

medium

newyorker

other-life

providence

quillette

TechCrunch

thenewrepublic

thestanfordreview

thestrategist

youtube

Ukraine

troops

ai-safety-newsletter

apnews

asia-times

asiatimes

Axios

brookings

cato

civitas

committee-on-oversight-and-government-reform

common-sense-media

coursera

digital-watch-observatory

european-comission

europeancommission

frontiers

futureoflifeinstitute

gov.uk

Intercept

international-ai-safety-report

latham-watkins

lemonde.fr

national-conference-of-state-legislatures

ncbi

restofworld

Reuters

shapingeurope’sdigitalfuture

stanford-medicine

the-daily-economy

thomsonreuters

Time

trump-white-house

unherd

us-senate-committee-on-finance

Verge

whitehouse

av-club

azfamily

cnet

exclaim

flickering-myth

focus-features

insession-film

los-angeles-times

mashable

rogerebert

screen-anarchy

screen-daily

sfchronicle

substack

sundance-institute

the-ai-doc

the-joy-of-movies

the-nerds-of-color

variety

we-live-entertainment

Wired

cybernews

foreignaffairs

googlebooks

jdsupra

nytimes

popularmechanics

space

thenewyorktimes

thetimes

wapo

futurism

linkedin

newscientist

gatesnotes.com

ourworldindata

simplilearn.com

waitbutwhy

wikipedia

AI Models Can Now Hack & Self-Replicate Across Servers

StudyAI observesModels AICan replicatesNow itselfHack & Self-Replicate Across Servers

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

LeCun

Marcus

Bengio

Hinton

Hassabis

Altman

Amodei

Musk

Go Deeper

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

AI Models Can Now Hack & Self-Replicate Across Servers

StudyAI observesModels AICan replicatesNow itselfHack & Self-Replicate Across Servers

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

LeCun

Marcus

Bengio

Hinton

Hassabis

Altman

Amodei

Musk

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