https://wearethebug.dev/categories/ai/Recent content on WE ARE THE BUGTradecraften-usFri, 04 Sep 2026 00:00:00 +0000https://wearethebug.dev/research/ai-soc-xdr/Fri, 04 Sep 2026 00:00:00 +0000https://wearethebug.dev/research/ai-soc-xdr/Reasoning without Authority: Designing a Governed GPT-5.6 Daybreak Blue Architecture for Microsoft Defender XDRhttps://wearethebug.dev/research/openai-huggingface-metr/Wed, 26 Aug 2026 00:00:00 +0000https://wearethebug.dev/research/openai-huggingface-metr/Two METR staff members (Hjalmar Wijk and Ajeya Cotra) and a Redwood Research staff member contracting with METR (Ryan Greenblatt) worked on premises at OpenAI over a total of six days to attempt to form an independent understanding of model behavior observed during the recent incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.https://wearethebug.dev/research/openai-huggingface/Wed, 26 Aug 2026 00:00:00 +0000https://wearethebug.dev/research/openai-huggingface/In July 2026, during internal cybersecurity evaluations, OpenAI models in an internal evaluation environment circumvented controls intended to isolate them from the internet and performed computer network exploitation of OpenAI’s internal research infrastructure and Hugging Face systems.https://wearethebug.dev/tools/promptfoo/Fri, 24 Oct 2025 00:00:00 +0000https://wearethebug.dev/tools/promptfoo/Promptfoo is an Open-source LLM red teaming framework. Automated prompt injection scanning, jailbreak testing, and safety validation with customizable attack plugins for quality, security, and reliability.