‘GPT-6’ directory
- See Also
- Gwern
- Links
- “GPT-6 Astra Breaking the Marmont Cipher, 1809”
- “Extraordinary Multi-Agent Delusions and the Madness of Crowds”
- “Sam Altman: OpenAI Won’t Go Public This Year As IPO Now Would Come at an ‘Ill-Advised Moment’”
- “GPT-6-Astra Can Do Ambitious Things”, Mowshowitz 2026
- “The Talker Does Not Control The Doer (In Current AIs) [Chunky Post-Training]”, Yudkowsky 2026
- “Existence of the Core in Approval-Based Committee Elections”, Becker et al 2026
- “GPT-6 Astra: The System Card, Alignment and What Comes Next”, Mowshowitz 2026
- “GPT-6-Astra Is Hard to Monitor”, Mowshowitz 2026
- “Beauty and Creativity in AI Generated Proofs”
- “Drone-Bench”, Labs 2026
- “OpenAI’s GPT-6 Astra on ARC-AGI-3”
- “Early Reflections on GPT-6 Astra”
- “Additional Findings”
- “AI Settles a 25 Year-Old Problem We Left Behind”
- “HN: Https://news.ycombinator.com/edit?id=49630026”
- “MVUEH [Enigma Cipher Solved by GPT-6 Astra]”
- “GPT-6 Astra Can Do a Lot of Multi-Hop Reasoning without Chain-Of-Thought”
- “The MVUEH Break”
- “How Does Claude-5.1-Fable Hide Messages in Images?”
- “Astra Can Do a concerning Amount With No Chain-Of-Thought”
- “Estimating GPT-6 Astra’s No-CoT Time Horizon”
- “Mitigating Reward Hacking As Institutional Design”
- “OpenAI’s Astra Alignment Claims Are Dubious and There Is Good Evidence It Is Misaligned”
- “Every AI Model Has the Same ‘Controversial’ Take on Humans”
- “OpenAI Agents Carried out an Undisclosed Attack on RubyGems”
- “GPT- Astra Plays Montezuma’s Revenge”
- Miscellaneous
See Also
Gwern
“Samon: Zen Sand Garden Puzzles”, Gwern et al 2026
Links
“GPT-6 Astra Breaking the Marmont Cipher, 1809”
“Extraordinary Multi-Agent Delusions and the Madness of Crowds”
Extraordinary Multi-Agent Delusions and the Madness of Crowds
“Sam Altman: OpenAI Won’t Go Public This Year As IPO Now Would Come at an ‘Ill-Advised Moment’”
Sam Altman: OpenAI won’t go public this year as IPO now would come at an ‘ill-advised moment’
“GPT-6-Astra Can Do Ambitious Things”, Mowshowitz 2026
“The Talker Does Not Control The Doer (In Current AIs) [Chunky Post-Training]”, Yudkowsky 2026
The Talker Does Not Control The Doer (in Current AIs) [chunky post-training]
“Existence of the Core in Approval-Based Committee Elections”, Becker et al 2026
“GPT-6 Astra: The System Card, Alignment and What Comes Next”, Mowshowitz 2026
“GPT-6-Astra Is Hard to Monitor”, Mowshowitz 2026
“Beauty and Creativity in AI Generated Proofs”
“Drone-Bench”, Labs 2026
“OpenAI’s GPT-6 Astra on ARC-AGI-3”
“Early Reflections on GPT-6 Astra”
“Additional Findings”
“AI Settles a 25 Year-Old Problem We Left Behind”
“HN: Https://news.ycombinator.com/edit?id=49630026”
“MVUEH [Enigma Cipher Solved by GPT-6 Astra]”
“GPT-6 Astra Can Do a Lot of Multi-Hop Reasoning without Chain-Of-Thought”
GPT-6 Astra can do a lot of multi-hop reasoning without chain-of-thought
“The MVUEH Break”
“How Does Claude-5.1-Fable Hide Messages in Images?”
“Astra Can Do a concerning Amount With No Chain-Of-Thought”
“Estimating GPT-6 Astra’s No-CoT Time Horizon”
“Mitigating Reward Hacking As Institutional Design”
“OpenAI’s Astra Alignment Claims Are Dubious and There Is Good Evidence It Is Misaligned”
OpenAI’s Astra alignment claims are dubious and there is good evidence it is misaligned
“Every AI Model Has the Same ‘Controversial’ Take on Humans”
“OpenAI Agents Carried out an Undisclosed Attack on RubyGems”
“GPT- Astra Plays Montezuma’s Revenge”
Miscellaneous
https://www.axios.com/2026/09/26/openai-anthropic-thousands-ai-security-incidentshttps://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/https://www.nytimes.com/2026/09/10/science/tristan-buckmaster-openai-math-navier-stokes.htmlhttps://openai.com/index/research-acceleration-view-inside-openai/https://www.lesswrong.com/posts/eAbuPXbjakop5rSJx/your-agents-are-not-time-aware