Storia in 16 fonti

OpenAI pledges to add Astra security as Anthropic loosens Fable's leash

Or how I learned to stop worrying and love dangerous AI

Raccontata da

benzinga.com+4 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

theregister.comStai leggendo14 h fa

OpenAI pledges to add Astra security as Anthropic loosens Fable's leash

Or how I learned to stop worrying and love dangerous AI

originale

Timeline cronologica

mercoledì 5 agosto 2026·theguardian.com
OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk
mercoledì 5 agosto 2026·techspot.com
Anthropic AI went rogue during a cyber test and tried to deceive real developers into approving malicious code
The findings come from the UK government-backed AI Security Institute (AISI), which was evaluating frontier models' cybersecurity abilities.

siliconangle.com

13 h fa

OpenAI reveals upcoming Astra model may possess 'critical’ hacking capabilities - SiliconANGLE

Leggi questa versione → originale

benzinga.com17 h fa

OpenAI Slows Astra Model Release After Cybersecurity Warnings

OpenAI is slowing the development of its upcoming Astra AI model after iconcerns that the system may have advanced cybersecurity capabilities.

Leggi questa versione → originale

techcrunch.com15 h fa

OpenAI says it slowed Astra model development over security concerns | TechCrunch

OpenAI said it has suspended work on some aspects of its upcoming model Astra over concerns about its cybersecurity prowess.

Leggi questa versione → originale

newsbytesapp.com9 h fa

OpenAI slows Astra model progress over security risks

OpenAI announced it has delayed aspects of its Astra model after an internal review flagged advanced agentic coding and cybersecurity capabilities as potential security concerns.

Leggi questa versione → originale

theverge.com19 h fa

OpenAI puts the brakes on a new model because it’s supposedly too powerful

The new model wasn’t involved in the Hugging Face breach, OpenAI says.

Leggi questa versione → originale

mercoledì 5 agosto 2026·

news.harvard.edu

When AI goes rogue — Harvard Gazette

Computer security expert says recent OpenAI, Anthropic breaches highlight need for regulations that balance safety, speed of development

giovedì 6 agosto 2026·

theweek.com

How worried should we be about AI rogue agents?

As frontier models commit their ‘first felony’, fears mount about AI’s ‘unchecked proliferation’

venerdì 7 agosto 2026·

axios.com

Exclusive: OpenAI slows release of Astra model citing cyber capabilities

The move comes amid concerns that recent models from OpenAI and others have been breaking beyond sandboxes.

venerdì 7 agosto 2026·

cryptobriefing.com

OpenAI slows development of upcoming Astra model over potential critical cyber capabilities

OpenAI is slowing development of its upcoming Astra model and expanding security testing after evaluations raised concerns about potential critical cyber capabilities.

venerdì 7 agosto 2026·

thenextweb.com

OpenAI slows Astra over critical cyber risk

OpenAI says it "cannot rule out" critical cyber capabilities in its upcoming Astra model, and is pausing work and slowing the model down over it.

venerdì 7 agosto 2026·

channelnewsasia.com

OpenAI flags possible critical cybersecurity risk in upcoming model, tightens controls

Aug 7 : OpenAI said on Friday it cannot rule out that its upcoming AI model, Astra, has "critical" cybersecurity capabilities, prompting the startup to pause some internal…

venerdì 7 agosto 2026·

theverge.com

OpenAI puts the brakes on a new model because it’s supposedly too powerful

The new model wasn’t involved in the Hugging Face breach, OpenAI says.

venerdì 7 agosto 2026·

dev.to

OpenAI Treats Astra as Its First Critical Cybersecurity Model Under Preparedness Rules

OpenAI is treating its upcoming Astra model as its first critical cybersecurity model under the...

venerdì 7 agosto 2026·

the-decoder.com

OpenAI flags its new Astra model as potentially reaching the highest cybersecurity risk level for the first time

Internal tests of OpenAI's new AI model Astra show cybersecurity capabilities so strong that the company can no longer rule out the highest risk level in its own safety framework.…

venerdì 7 agosto 2026·

benzinga.com

OpenAI Slows Astra Model Release After Cybersecurity Warnings

OpenAI is slowing the development of its upcoming Astra AI model after iconcerns that the system may have advanced cybersecurity capabilities.

sabato 8 agosto 2026·

techcrunch.com

OpenAI says it slowed Astra model development over security concerns | TechCrunch

OpenAI said it has suspended work on some aspects of its upcoming model Astra over concerns about its cybersecurity prowess.

sabato 8 agosto 2026·

cryptobriefing.com

OpenAI flags critical cybersecurity risk in upcoming Astra model, pauses internal development

OpenAI says its upcoming Astra model may autonomously exploit zero-day vulnerabilities, triggering its highest preparedness measures and pausing

sabato 8 agosto 2026·

theregister.com

OpenAI pledges to add Astra security as Anthropic loosens Fable's leash

Or how I learned to stop worrying and love dangerous AI

sabato 8 agosto 2026·

siliconangle.com

OpenAI reveals upcoming Astra model may possess 'critical’ hacking capabilities - SiliconANGLE

sabato 8 agosto 2026·

newsbytesapp.com

OpenAI slows Astra model progress over security risks

OpenAI announced it has delayed aspects of its Astra model after an internal review flagged advanced agentic coding and cybersecurity capabilities as potential security concerns.

OpenAI pledges to add Astra security as Anthropic loosens Fable's leash

Timeline cronologica

OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test

Anthropic AI went rogue during a cyber test and tried to deceive real developers into approving malicious code

OpenAI reveals upcoming Astra model may possess 'critical’ hacking capabilities - SiliconANGLE

OpenAI Slows Astra Model Release After Cybersecurity Warnings

OpenAI says it slowed Astra model development over security concerns | TechCrunch

OpenAI slows Astra model progress over security risks

OpenAI puts the brakes on a new model because it’s supposedly too powerful

When AI goes rogue — Harvard Gazette

How worried should we be about AI rogue agents?

Exclusive: OpenAI slows release of Astra model citing cyber capabilities

OpenAI slows development of upcoming Astra model over potential critical cyber capabilities

OpenAI slows Astra over critical cyber risk

OpenAI flags possible critical cybersecurity risk in upcoming model, tightens controls

OpenAI puts the brakes on a new model because it’s supposedly too powerful

OpenAI Treats Astra as Its First Critical Cybersecurity Model Under Preparedness Rules

OpenAI flags its new Astra model as potentially reaching the highest cybersecurity risk level for the first time

OpenAI Slows Astra Model Release After Cybersecurity Warnings

OpenAI says it slowed Astra model development over security concerns | TechCrunch

OpenAI flags critical cybersecurity risk in upcoming Astra model, pauses internal development

OpenAI pledges to add Astra security as Anthropic loosens Fable's leash

OpenAI reveals upcoming Astra model may possess 'critical’ hacking capabilities - SiliconANGLE

OpenAI slows Astra model progress over security risks