Storia in 19 fonti

GPT-6 Astra might be too powerful to understand or control

OpenAI is hailing its new model as “the world’s most intelligent and aligned”, but the details reveal an awareness of being evaluated and an ability to manipulate its visible reasoning

Raccontata da

infoworld.com+7 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

transformernews.aiStai leggendo6 g fa

GPT-6 Astra might be too powerful to understand or control

OpenAI is hailing its new model as “the world’s most intelligent and aligned”, but the details reveal an awareness of being evaluated and an ability to manipulate its visible reasoning

originale

Timeline cronologica

martedì 1 settembre 2026·fortune.com
OpenAI to limit access to Astra model's advanced cyber features due to hacking concerns | Fortune
OpenAI says Astra is considerably more capable at cyber tasks than GPT-5.6 Sol. Following the Hugging Face incident, it is being especially cautious about releasing it.
giovedì 3 settembre 2026·cnbc.com
OpenAI begins rolling out Astra model after warning of its advanced cyber capabilities
OpenAI said companies participating in its application-based cybersecurity program will be first to get access to Astra.

GPT-6 Astra might be too powerful to understand or control

Confronto fonti

GPT-6 Astra might be too powerful to understand or control

Timeline cronologica

OpenAI to limit access to Astra model's advanced cyber features due to hacking concerns | Fortune

OpenAI begins rolling out Astra model after warning of its advanced cyber capabilities

OpenAI officially launches GPT-6 Astra: How to try it

OpenAI launches GPT-6 Astra, 'the world’s most intelligent and aligned model' that you can't use just yet

OpenAI unveils 'world's most intelligent model' Astra with cyber security in focus | The National

GPT-6 Astra Scores 100% on ExploitBench as OpenAI Blocks PoC Exploit Requests

OpenAI releases new model that it says triggered internal security measures

OpenAI releases new model that it says triggered internal security measures

GPT-6 Astra Is Here—and OpenAI Thinks It May Kick Off the AGI Era

OpenAI launches GPT-6 Astra, its most powerful model yet, and touts its ability to use your computer | Fortune

OpenAI Releases GPT-6 Astra: The Closest AI Model Yet to AGI - Decrypt

GPT-6 Astra is the first model making OpenAI willing to declare the "AGI era"

OpenAI rolls out new AI model GPT-6 Astra

OpenAI launches GPT-6 Astra amid fears of cybersecurity risks

OpenAI launches GPT-6 Astra, 'the world’s most intelligent and aligned model' that you can't use just yet

OpenAI officially launches GPT-6 Astra: How to try it

OpenAI Astra Rolls Out With Alignment Controls and Restricted Cybersecurity Access

OpenAI launches GPT-6 Astra, its first model to cross a critical cybersecurity threshold

OpenAI unveils GPT-6 Astra model with cyber guardrails

OpenAI rolls out GPT-6 astra model with cyber guardrails

OpenAI begins rollout of GPT-6 amid growing scrutiny over safety

OpenAI unveils latest AI model amid rising scrutiny and safety concerns

OpenAI begins rollout of new powerful AI model GPT-6 Astra

GPT-6 Astra is here: OpenAI’s new AI model can use computers, browse web and get work done

OpenAI выпустила GPT‑6 Astra — модель, которая сама находит уязвимости нулевого дня и достигает паритета с человеком по тесту ARC‑AGI‑3