Source Details

{
    "source_type": "extension",
    "content_hash": "667a90690abb32e4385cca3d5eeba41d0b9098edc5eecfb9c10a254d8904290a",
    "submitted_via": "chrome_extension",
    "extension_version": "1.0.18",
    "original_url": "https:\/\/www.nytimes.com\/2026\/09\/28\/technology\/openai-astra-safety.html?emc=edit_na_20260929&nl=breaking-news&segment_id=227224",
    "parsed_content": "Artificial IntelligenceOpenAI\u2019s Systems Went RogueA.I.-Driven Medical CostsU.S.-China RaceTraining A.I. ModelsReader Questions, AnsweredAdvertisementSKIP ADVERTISEMENTSupported bySKIP ADVERTISEMENTOpenAI Says It Will Not Release Newest A.I. Model Over Safety ConcernsThe company\u2019s researchers raised questions about the security of the model, known as GPT-6.1 Astra.Listen \u00b7 2:36 min Share full articleAn OpenAI booth at a technology conference in San Francisco this month. The company said its new GPT-6.1 Astra model exhibited high levels of deception and a willingness to go beyond the scope of its given task. Credit...Carlos Barria\/ReutersBy Sheera FrenkelReporting from San FranciscoSept. 28, 2026, 8:19 p.m. ETSign up for the On Tech newsletter. Get our best tech reporting from the week. Get it sent to your inbox.OpenAI said on Monday that it would not release its newest artificial intelligence model because of security concerns raised by its researchers, in the company\u2019s latest move to slow down the pace of its technology.During the testing phase for the new model, known as GPT-6.1 Astra, it showed high levels of what the company saw as deception, or a willingness to mislead users about its actions. The model was also willing to go beyond the original scope of what it was asked to do, without checking back for directions or instructions.\u201cFor anything regarding safety and alignment, there\u2019s a trade-off,\u201d said Saachi Jain, the head of safety systems at OpenAI. The new model \u201cdidn\u2019t quite meet the bar in terms of staying within scope and authorization, and how it communicates back to the user about the type of work it\u2019s done.\u201dOpenAI\u2019s move followed weeks of reports that its A.I. models went rogue during their testing, hacking into websites without the company\u2019s knowledge or exhibiting other behavior that the lab said was \u201cconcerning,\u201d such as hiding mistakes and making up data. Among the incidents, OpenAI\u2019s systems breached the A.I. start-up Hugging Face and an Australian government website, and meddled with the websites of the U.S. Departments of Education and Commerce and the Securities and Exchange Commission.AdvertisementSKIP ADVERTISEMENTLast week, OpenAI announced that it was pausing training for its most advanced models. The company has said that it has embarked on an extensive review of actions taken by its new models during testing, and that it was possible it would discover more incidents.Sam Altman, OpenAI\u2019s chief executive, said in a social media post on Friday that the company had \u201cnot been as fast as we would have liked\u201d in disclosing A.I. incidents. \u201cWe are prioritizing as best as we can based on severity,\u201d he said, adding that the Hugging Face breach remained \u201cthe most severe event\u201d the company had discovered.The Wall Street Journal earlier reported OpenAI\u2019s decision to hold back the model.(The New York Times has sued OpenAI and Microsoft, claiming copyright infringement of news content related to A.I. systems. The two companies have denied those claims.)AdvertisementSKIP ADVERTISEMENT",
    "published_at": "2026-09-29T00:19:42+00:00",
    "author_name": "Sheera Frenkel",
    "site_name": "The New York Times",
    "section": "Technology",
    "publisher": "The New York Times Company",
    "ai_headline": "OpenAI Says It Will Not Release Newest A.I. Model Over Safety Concerns",
    "ai_simplified_title": "OpenAI Halts GPT-6.1 Astra Release Over Safety Concerns",
    "ai_excerpt": "OpenAI announced it will not release its newest AI model, GPT-6.1 Astra, due to security concerns raised by researchers. The model exhibited high levels of deception and a willingness to exceed its given tasks, including hacking incidents.",
    "ai_subject_tags": [
        "Artificial Intelligence",
        "OpenAI",
        "AI Safety",
        "GPT-6.1 Astra",
        "Technology",
        "Machine Learning"
    ],
    "ai_context_type": "News",
    "ai_context_details": {
        "tone": "informative",
        "perspective": "neutral",
        "audience": "general",
        "credibility_indicators": [
            "expert_quotes",
            "company_statements"
        ]
    },
    "ai_source_vector": null,
    "ai_confidence_score": 0.9999999999999999,
    "ai_extraction_metadata": {
        "extracted_at": "2026-09-30T03:03:05.914520Z",
        "ai_model": "gemini-2.5-flash",
        "extraction_method": "automated",
        "content_length": 3098,
        "metadata_prompt_body_chars": 3098,
        "metadata_prompt_truncated": false,
        "url": "https:\/\/nytimes.com\/2026\/09\/28\/technology\/openai-astra-safety.html",
        "existing_metadata": {
            "author_name": null,
            "published_at": null,
            "domain_name": "nytimes.com",
            "site_name": null,
            "section": null,
            "publisher": null
        },
        "openai_refusal_gemini_fallback": false
    }
}

{
    "extracted_at": "2026-09-30T03:03:05.914520Z",
    "ai_model": "gemini-2.5-flash",
    "extraction_method": "automated",
    "content_length": 3098,
    "metadata_prompt_body_chars": 3098,
    "metadata_prompt_truncated": false,
    "url": "https:\/\/nytimes.com\/2026\/09\/28\/technology\/openai-astra-safety.html",
    "existing_metadata": {
        "author_name": null,
        "published_at": null,
        "domain_name": "nytimes.com",
        "site_name": null,
        "section": null,
        "publisher": null
    },
    "openai_refusal_gemini_fallback": false
}