出典リンク一覧 本日のトップニュース • OpenAI is now using AI to attack its own AI, and it's working better than humans ever did (https://the-decoder.com/openai-is-now-using-ai-to-attack-its-own-ai-and-its-working-better-than-humans-ever-did/) • GPT-Red: Unlocking Self-Improvement for Robustness (https://openai.com/index/unlocking-self-improvement-gpt-red) • Simulating everything, sort of: The promise and limits of world models (https://arstechnica.com/ai/2026/07/simulating-everything-sort-of-the-promise-and-limits-of-world-models/)
注目の深掘り • Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer (https://www.technologyreview.com/2026/07/15/1140514/meet-gpt-red-an-llm-super-hacker-openai-built-to-make-its-models-safer/)
