A developer argues that the era of verbose 'act as an expert' prompts is over, advocating for 'master prompts' as a stable policy layer above individual tasks. The piece details a structured framework…
A workshop on Chain of Thought (CoT) monitorability revealed that the alliance between CoT and monitoring is fragile, as CoT was developed for capability improvements, not transparency. Researchers in…
A developer compiled a comprehensive defensive knowledge base cataloguing known prompt-injection and jailbreak patterns, the models and systems they have affected, and the defenses against them. The r…
Current evaluation methods for large language models (LLMs) are fundamentally reactive and fail to anticipate qualitative shifts in capabilities, such as emergent abilities or strategic information wi…