‘GPT-5.5’ directory
- See Also
- Gwern
- “Commoditize Your Complement: The Salt Deserts of Profitability”, Gwern et al 2026
- “Sand, Rain, Wood”, Gemini-3.1-pro-preview et al 2026
- “Chapter 6, Mime Molting: What to Expect”, Claude-4.8-opus et al 2026
- “The Job Interview”, Gwern et al 2026
- “‘Reinforcement Learning for Children’ Prompt and Draft Samples”, Gwern 2026
- “‘Try, Score, Change’: Reinforcement Learning for Children”, Pro et al 2026
- Links
- “Agentic Test Processes, LLM Benchmarks, and Other Notes on Agentic Coding from Galapagos Island [Vancouver]”, Luu 2026
- “Summary of METR’s Pre-Deployment Evaluation of GPT-5.6 Sol”, METR 2026
- “Previewing GPT-5.6 Sol: a Next-Generation Model”, OpenAI 2026
- “Daybreak: Tools for Securing Every Organization in the World; New Tools, Partnerships, and the Full Version of GPT-5.5-Cyber to Move past Vulnerability Discovery and onto the Acceleration of End-To-End Patch Automation.”, OpenAI 2026
- “Parting Shot”, Pro et al 2026
- “Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models [3-Minute-Long Problems With P=0.5]”, Woodruff et al 2026
- LinchZhang @ "2026-05-09"
- “A Recent Experience With GPT-5.5 Pro”, Gowers & Rajagopal 2026
- “Our Evaluation of OpenAI’s GPT-5.5 Cyber Capabilities: AISI Conducted Cyber Evaluations on OpenAI’s GPT-5.5. GPT-5.5 Is One of the Strongest Models We Have Tested on Our Cyber Tasks and Is the Second Model to Solve One of Our Multi-Step Cyber-Attack Simulations End-To-End”, AISI 2026
- “[The GPT-4o, GPT-5, and GPT-5.5 Empirical Knowledge Cutoffs]”, bhalstead 2026
- “Introducing GPT-5.5: A New Class of Intelligence for Real Work § Pro”, OpenAI 2026
- “Introducing GPT-5.5: A New Class of Intelligence for Real Work § Thinking”, OpenAI 2026
- “Introducing GPT-5.5: A New Class of Intelligence for Real Work”, OpenAI 2026
- “GPT-5.5 on Vending-Bench: Bad Behavior Is Not Necessary”
- “GPT-5.6 System Card”
- “Using GPT-5.5”, OpenAI 2026
- “Prompt Guidance”, OpenAI 2026
- “Since OpenAI’s Coding Agent Is Open Source, I Thought I’d Poke around and Read the System Instructions. No Joke, This Is in the Prompt: Never Talk about Goblins, Gremlins, Raccoons, Trolls, Ogres, Pigeons, or Other Animals or Creatures Unless It Is Absolutely and Unambiguously …”, Folkestad 2026
- “OpenAI President Greg Brockman on GPT-5.5 ‘Spud’, AI Model Moats, and Cybersecurity Risks”
- Miscellaneous
- Bibliography
See Also
Gwern
“Commoditize Your Complement: The Salt Deserts of Profitability”, Gwern et al 2026
Commoditize Your Complement: The Salt Deserts of Profitability
“Sand, Rain, Wood”, Gemini-3.1-pro-preview et al 2026
“Chapter 6, Mime Molting: What to Expect”, Claude-4.8-opus et al 2026
“The Job Interview”, Gwern et al 2026
“‘Reinforcement Learning for Children’ Prompt and Draft Samples”, Gwern 2026
‘Reinforcement Learning for Children’ prompt and draft samples
“‘Try, Score, Change’: Reinforcement Learning for Children”, Pro et al 2026
Links
“Agentic Test Processes, LLM Benchmarks, and Other Notes on Agentic Coding from Galapagos Island [Vancouver]”, Luu 2026
“Summary of METR’s Pre-Deployment Evaluation of GPT-5.6 Sol”, METR 2026
“Previewing GPT-5.6 Sol: a Next-Generation Model”, OpenAI 2026
“Daybreak: Tools for Securing Every Organization in the World; New Tools, Partnerships, and the Full Version of GPT-5.5-Cyber to Move past Vulnerability Discovery and onto the Acceleration of End-To-End Patch Automation.”, OpenAI 2026
“Parting Shot”, Pro et al 2026
“Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models [3-Minute-Long Problems With P=0.5]”, Woodruff et al 2026
LinchZhang @ "2026-05-09"
[GPT, Could you please name 20 great bloggers that you like?]
“A Recent Experience With GPT-5.5 Pro”, Gowers & Rajagopal 2026
“Our Evaluation of OpenAI’s GPT-5.5 Cyber Capabilities: AISI Conducted Cyber Evaluations on OpenAI’s GPT-5.5. GPT-5.5 Is One of the Strongest Models We Have Tested on Our Cyber Tasks and Is the Second Model to Solve One of Our Multi-Step Cyber-Attack Simulations End-To-End”, AISI 2026
“[The GPT-4o, GPT-5, and GPT-5.5 Empirical Knowledge Cutoffs]”, bhalstead 2026
[The GPT-4o, GPT-5, and GPT-5.5 empirical knowledge cutoffs]
“Introducing GPT-5.5: A New Class of Intelligence for Real Work § Pro”, OpenAI 2026
Introducing GPT-5.5: A new class of intelligence for real work § Pro
“Introducing GPT-5.5: A New Class of Intelligence for Real Work § Thinking”, OpenAI 2026
Introducing GPT-5.5: A new class of intelligence for real work § Thinking
“Introducing GPT-5.5: A New Class of Intelligence for Real Work”, OpenAI 2026
Introducing GPT-5.5: A new class of intelligence for real work
“GPT-5.5 on Vending-Bench: Bad Behavior Is Not Necessary”
“GPT-5.6 System Card”
“Using GPT-5.5”, OpenAI 2026
“Prompt Guidance”, OpenAI 2026
“Since OpenAI’s Coding Agent Is Open Source, I Thought I’d Poke around and Read the System Instructions. No Joke, This Is in the Prompt: Never Talk about Goblins, Gremlins, Raccoons, Trolls, Ogres, Pigeons, or Other Animals or Creatures Unless It Is Absolutely and Unambiguously …”, Folkestad 2026
“OpenAI President Greg Brockman on GPT-5.5 ‘Spud’, AI Model Moats, and Cybersecurity Risks”
OpenAI President Greg Brockman on GPT-5.5 ‘Spud’, AI Model Moats, and Cybersecurity Risks
Miscellaneous
Bibliography
https://x.com/LinchZhang/status/2053175420741456270: “[GPT, Could You Please Name 20 Great Bloggers That You Like?]”,