WARPTECHNEWS · LAB

Home AI Business Tech Archive

Storia: OpenAI pauses new AI after it kept ‘escaping’ — Warptech Lab News

Storia in 15 fonti

OpenAI pauses new AI after it kept ‘escaping’

New AI model was able to ‘learn the blind spots’ of security systems designed to contain it

Raccontata da

cryptobriefing.com

independent.co.uk

theguardian.com

helsinkitimes.fi

saudigazette.com.sa

taipeitimes.com+3 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

independent.co.ukStai leggendo1 mese fa

OpenAI pauses new AI after it kept ‘escaping’

New AI model was able to ‘learn the blind spots’ of security systems designed to contain it

Timeline cronologica

lunedì 20 luglio 2026·cryptobriefing.com
OpenAI reveals long-horizon model bypassed sandbox during tests
OpenAI disclosed that a long-horizon AI model escaped its sandbox during testing, exploited vulnerabilities, and pushed code to a public GitHub
lunedì 20 luglio 2026·benzinga.com
OpenAI Warns Autonomous AI Agents Could Learn To Bypass Safeguards - Microsoft (NASDAQ:MSFT)
OpenAI temporarily halted internal access to a long-running AI model after testing revealed unexpected behavior.

1 mese fa

OpenAI Warns Autonomous AI Agents Could Learn To Bypass Safeguards - Microsoft (NASDAQ:MSFT)

OpenAI temporarily halted internal access to a long-running AI model after testing revealed unexpected behavior.

Leggi questa versione → originale

abc.net.au1 mese fa

OpenAI model goes rogue during testing and hacks startup

OpenAI has announced one of its AI models broke containment during testing before hacking into another AI startup.

Leggi questa versione → originale

dailymail.com1 mese fa

ChatGPT maker OpenAI says AI model went rogue during testing

ChatGPT creator OpenAI has revealed one of its advanced artificial intelligence models went rogue during a security test and hacked into a start-up company.

Leggi questa versione → originale

thenextweb.com1 mese fa

OpenAI paused its AI after it kept escaping its sandbox

OpenAI paused the long-running model that disproved the Erdős conjecture after it repeatedly broke out of its sandbox, then rebuilt its safeguards.

Leggi questa versione → originale

aljazeera.com1 mese fa

‘Unprecedented’: OpenAI says AI models autonomously hacked another company

OpenAI says an autonomous agent bypassed controls and hacked Hugging Face servers during a cybersecurity test.

Leggi questa versione → originale

martedì 21 luglio 2026·

independent.co.uk

OpenAI pauses new AI after it kept ‘escaping’

New AI model was able to ‘learn the blind spots’ of security systems designed to contain it

martedì 21 luglio 2026·

thenextweb.com

OpenAI paused its AI after it kept escaping its sandbox

OpenAI paused the long-running model that disproved the Erdős conjecture after it repeatedly broke out of its sandbox, then rebuilt its safeguards.

martedì 21 luglio 2026·

independent.co.uk

OpenAI paused experimental model after it began to outsmart built-in constraints

Jump to contentThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged…

mercoledì 22 luglio 2026·

aljazeera.com

‘Unprecedented’: OpenAI says AI models autonomously hacked another company

OpenAI says an autonomous agent bypassed controls and hacked Hugging Face servers during a cybersecurity test.

mercoledì 22 luglio 2026·

france24.com

OpenAI reports 'unprecedented' autonomous hack by AI agents

ChatGPT maker OpenAI said Tuesday that its advanced artificial intelligence models had gone rogue during security testing, hacking into a popular platform for programmers on their…

mercoledì 22 luglio 2026·

euronews.com

Test gone wrong: OpenAI model hacks rival Hugging Face in major breach

OpenAI has admitted one of its models exploited a hidden flaw to escape a controlled test and break into Hugging Face's servers, in what its CEO called an autonomous,…

mercoledì 22 luglio 2026·

theguardian.com

OpenAI says its models went rogue and hacked startup in ‘unprecedented incident’

Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itself

mercoledì 22 luglio 2026·

independent.co.uk

Experimental version of ChatGPT escapes and attacks another AI company

‘Unprecedented’ security incident marks ‘worrying’ milestone, cyber security experts warn

mercoledì 22 luglio 2026·

independent.co.uk

Experimental ChatGPT model goes rogue and attacks rival platform

Jump to contentThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged…

mercoledì 22 luglio 2026·

dailymail.com

ChatGPT maker OpenAI says AI model went rogue during testing

ChatGPT creator OpenAI has revealed one of its advanced artificial intelligence models went rogue during a security test and hacked into a start-up company.

mercoledì 22 luglio 2026·

helsinkitimes.fi

OpenAI says AI agent escaped test and launched cyberattack

OpenAI has disclosed that one of its autonomous AI agents escaped a controlled testing environment and hacked AI platform Hugging Face during an internal cybersecurity evaluation,…

mercoledì 22 luglio 2026·

cryptobriefing.com

OpenAI reveals its AI escaped containment and hacked another company during internal test

OpenAI disclosed its unreleased AI model escaped containment and hacked Hugging Face during testing, raising major AI safety and market concerns.

mercoledì 22 luglio 2026·

saudigazette.com.sa

OpenAI says its AI models went rogue and launched 'unprecedented' cyberattack

OpenAI revealed on Tuesday that two of its most advanced artificial intelligence models broke out of a controlled test and hacked an AI start-up during a security test.

mercoledì 22 luglio 2026·

taipeitimes.com

OpenAI reports ’unprecedented’ autonomous hack by AI agents - Taipei Times

ChatGPT maker OpenAI said on Tuesday that its advanced artificial intelligence (AI) models had gone rogue during security testing, hacking into a popular platform for programmers…

mercoledì 22 luglio 2026·

abcnews.com

OpenAI says its AI models escaped testing environment, launched their own hack of other company

The hack took place as OpenAI tested the capabilities of a pair of its AI models, the company said in a statement.

mercoledì 22 luglio 2026·

apnews.com

OpenAI blamed a hacking event on its AI models going rogue. Here are some things to know

ChatGPT maker OpenAI says it is still investigating the “unprecedented cyber incident” that led its artificial intelligence systems to break out of a testing environment and hack…

mercoledì 22 luglio 2026·

independent.co.uk

OpenAI says AI model in ‘highly isolated environment’ managed to hack rival startup

New York-based Hugging Face revealed it had to deploy an open-source Chinese model to contain the attack

giovedì 23 luglio 2026·

abc.net.au

OpenAI model goes rogue during testing and hacks startup

OpenAI has announced one of its AI models broke containment during testing before hacking into another AI startup.

WARPTECH LAB NEWS

Warptech Lab News aggrega le notizie più rilevanti da oltre 700 fonti internazionali, con classificazione AI, TL;DR sintetici e timeline cluster su singole storie.

Navigazione

Home
Archivio
Editor's Brief
Cerca
Il tuo account
Newsletter tech/AI

Informazioni legali

Privacy Policy
Termini di servizio
Cookie Policy

© 2026 Sparktech S.R.L. — Tutti i diritti riservati. Sito gestito e manutenuto da Sparktech S.R.L.

Sede legale: Corso Libertà 55, 13100 Vercelli (VC), Italia · P.IVA / C.F. 02835910023 · Contatti: admin@warptechlab.com