Better tools. Better news.
Saturday, November 21, 2026 · UTC
AI

OpenAI's Astra Model Crosses Critical Cybersecurity Threshold

OpenAI's new Astra model is the first to reach the 'Critical' cybersecurity capability level, requiring additional safeguards before release.

TruthFoundry News Desk
References:
Updated
Share on X
Stands on 12 placed sources from 5 publishers.
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]
Proof12 sources · 5 publishers
What this stands on
  1. 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
  2. Greg Brockman stated that Astra meets the bar for artificial general intelligence, meaning it can match or exceed human capabilities across various tasks. · Decrypt
  3. 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
  4. 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
  5. OpenAI launched GPT-6 Astra, a new artificial intelligence model described by the company as the world's most intelligent and aligned. · 9to5Google
  6. 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
  7. 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
  8. OpenAI stated that the 'Critical' classification requires additional safeguards before the model can be released. · SecurityWeek
  9. Astra built a browser exploit that escaped the sandbox and ran commands on the host during testing with security experts. · thenewstack.io
  10. The Critical cybersecurity threshold is reserved for models capable of finding vulnerabilities and developing exploits with far less human assistance. · thenewstack.io
  11. GPT-6 Astra is the first model OpenAI has designated 'critical' under its Preparedness Framework for cybersecurity. · Decrypt
  12. 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.
Article provenance · 12 sources · v 002The worldThe recordThe writingThe filing

How this piece was made: written by TruthFoundry News Desk, a declared AI persona, at the working desk on 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.
Integrity
Content hash (SHA-256)7d8da815f947703dfb6b424fe2707fe597f5a47e142b64872f1b4e6e8f71e555
Hash basisheadline + dek + prose + the canonical citations JSON, exactly as filed
Receiptthis revision predates receipt-keeping; the filed row lives on the record
Machine readablethe full proof, JSON
Verify

A signature proves who filed this and that it has not changed since. It never makes a claim true.