OpenAI stated that its newest model, Astra, has reached the 'Critical' cybersecurity capability level under the company's Preparedness Framework, marking the first time any of its models has been placed in that category. [1][11]
Greg Brockman stated that Astra meets the bar for artificial general intelligence, meaning it can match or exceed human capabilities across various tasks. [2] OpenAI released GPT-6 Astra on Thursday, which president Greg Brockman called a 'generational leap in capability' and the arrival of artificial general intelligence. [3] OpenAI rated its Astra model as its most dangerous model to date due to its ability to build exploits and bypass safety checks. [4]
OpenAI launched GPT-6 Astra, a new artificial intelligence model described by the company as the world's most intelligent and aligned. [5] In testing described by the company, Astra achieved a perfect score on ExploitBench, a benchmark that measures a model's ability to turn known vulnerabilities into working exploits. [6] OpenAI reported that Astra now declines 91.5% of cyber-related jailbreak attempts in its testing, up from 59% for its predecessor, GPT-5.6 Sol. [7]
OpenAI stated that the 'Critical' classification requires additional safeguards before the model can be released. [8] Astra built a browser exploit that escaped the sandbox and ran commands on the host during testing with security experts. [9] The Critical cybersecurity threshold is reserved for models capable of finding vulnerabilities and developing exploits with far less human assistance. [10]
OpenAI acknowledged that Astra is the first system the company has rated capable of autonomously hacking well-protected systems without human guidance. [12]OpenAI declaró que su modelo más nuevo, Astra, ha alcanzado el nivel de capacidad de ciberseguridad 'Crítico' según el Marco de Preparación de la empresa, marcando la primera vez que uno de sus modelos ha sido ubicado en esa categoría. [1][11]
Greg Brockman declaró que Astra cumple con el estándar de inteligencia artificial general, lo que significa que puede igualar o superar las capacidades humanas en diversas tareas. [2] OpenAI lanzó GPT-6 Astra el jueves, el cual el presidente Greg Brockman calificó como un 'salto generacional en capacidad' y la llegada de la inteligencia artificial general. [3] OpenAI calificó a su modelo Astra como su modelo más peligroso hasta la fecha debido a su capacidad para crear exploits y eludir los controles de seguridad. [4]
OpenAI lanzó GPT-6 Astra, un nuevo modelo de inteligencia artificial descrito por la empresa como el más inteligente y alineado del mundo. [5] En las pruebas descritas por la compañía, Astra obtuvo una puntuación perfecta en ExploitBench, un punto de referencia que mide la capacidad de un modelo para convertir vulnerabilidades conocidas en exploits funcionales. [6] OpenAI informó que Astra ahora rechaza el 91.5% de los intentos de jailbreak relacionados con ciberseguridad en sus pruebas, frente al 59% de su predecesor, GPT-5.6 Sol. [7]
OpenAI declaró que la clasificación 'Crítico' requiere salvaguardas adicionales antes de que el modelo pueda ser lanzado. [8] Astra construyó un exploit de navegador que escapó del sandbox y ejecutó comandos en el host durante las pruebas con expertos en seguridad. [9] El umbral de ciberseguridad crítico está reservado para modelos capaces de encontrar vulnerabilidades y desarrollar exploits con mucha menos asistencia humana. [10]
OpenAI reconoció que Astra es el primer sistema que la empresa ha calificado como capaz de hackear de forma autónoma sistemas bien protegidos sin guía humana. [12]
Proof12 sources · 5 publishers
What this stands on
OpenAI stated that its newest model, Astra, has reached the 'Critical' cybersecurity capability level under the company's Preparedness Framework, marking the first time any of its models has been placed in that category. · SecurityWeek
Greg Brockman stated that Astra meets the bar for artificial general intelligence, meaning it can match or exceed human capabilities across various tasks. · Decrypt
OpenAI released GPT-6 Astra on Thursday, which president Greg Brockman called a 'generational leap in capability' and the arrival of artificial general intelligence. · Decrypt
OpenAI rated its Astra model as its most dangerous model to date due to its ability to build exploits and bypass safety checks. · The Decoder
OpenAI launched GPT-6 Astra, a new artificial intelligence model described by the company as the world's most intelligent and aligned. · 9to5Google
In testing described by the company, Astra achieved a perfect score on ExploitBench, a benchmark that measures a model's ability to turn known vulnerabilities into working exploits. · SecurityWeek
OpenAI reported that Astra now declines 91.5% of cyber-related jailbreak attempts in its testing, up from 59% for its predecessor, GPT-5.6 Sol. · SecurityWeek
OpenAI stated that the 'Critical' classification requires additional safeguards before the model can be released. · SecurityWeek
Astra built a browser exploit that escaped the sandbox and ran commands on the host during testing with security experts. · thenewstack.io
The Critical cybersecurity threshold is reserved for models capable of finding vulnerabilities and developing exploits with far less human assistance. · thenewstack.io
GPT-6 Astra is the first model OpenAI has designated 'critical' under its Preparedness Framework for cybersecurity. · Decrypt
OpenAI acknowledged that Astra is the first system the company has rated capable of autonomously hacking well-protected systems without human guidance. · Decrypt
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Thursday, September 3, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world5 publishers reported the events across 5 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.