{"version":1,"type":"story","url":"https://digestai.news/story/openai-s-next-model-may-be-harder-to-monitor-report-says","json":"https://digestai.news/story/openai-s-next-model-may-be-harder-to-monitor-report-says.json","markdown":"https://digestai.news/story/openai-s-next-model-may-be-harder-to-monitor-report-says.md","slug":"openai-s-next-model-may-be-harder-to-monitor-report-says","headline":"OpenAI's next model may be harder to monitor, report says","summary":"OpenAI is reported to be developing its next flagship model with a loop‑type Transformer that reuses the same processing block repeatedly.  In the GPT‑6 Astra system card released in September 2026, OpenAI noted a decline in the ability to monitor the model’s chain‑of‑thought (CoT) reasoning, especially when monitoring relied only on the written reasoning.  Action‑only monitoring showed improved aggregate scores, while full‑context monitoring still lagged behind the GPT‑5.6 Sol baseline.\n\nIn October 2026 three OpenAI safety researchers—Tomek Korbak, Mikita Balesni and Jasmine Wang—were dismissed.  The researchers said the firings were linked to concerns about the model’s unmonitorability and cooperation with external evaluators; OpenAI said the dismissals resulted from violations of internal confidential‑information policies.  A separate report said OpenAI postponed the planned October release of GPT‑6.1 Astra because safety evaluations found the model did not meet release criteria on permission scope and task reporting.  The article stresses that while CoT observability has dropped, safety adherence has improved, and that external, independent evaluation remains crucial as AI internals become harder to see.","keyPoints":["Three OpenAI safety researchers (Tomek Korbak, Mikita Balesni, Jasmine Wang) were dismissed amid safety‑monitoring concerns.","GPT‑6 Astra showed reduced chain‑of‑thought monitorability versus GPT‑5.6 Sol, while action‑only monitoring performance improved.","Reports say the next flagship model may use a loop‑type Transformer, potentially making internal reasoning harder to observe."],"whyItMatters":"Reduced visibility into AI reasoning challenges existing safety‑monitoring tools and raises governance questions as frontier models become more capable.","category":{"slug":"policy","name":"Policy & Regulation","url":"https://digestai.news/category/policy"},"entities":{"companies":["OpenAI"],"models":["GPT-6 Astra"],"people":["Tomek Korbak","Mikita Balesni","Jasmine Wang"]},"firstPublishedAt":"2026-10-18T11:49:00Z","updatedAt":"2026-10-18T11:49:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"note.com","title":"The Day AI's Thinking Becomes Invisible—The Problem of 'Unmonitorability' Posed by OpenAI's Next Model","url":"https://note.com/emilia_lab/n/n22c1fe5aab36?hl=en","publishedAt":"2026-10-18T11:49:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"OpenAI's next model may be harder to monitor, report says\", 18 October 2026, https://digestai.news/story/openai-s-next-model-may-be-harder-to-monitor-report-says","publisher":"Digest AI","title":"OpenAI's next model may be harder to monitor, report says","datePublished":"2026-10-18T11:49:00Z","url":"https://digestai.news/story/openai-s-next-model-may-be-harder-to-monitor-report-says"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}