Definition
Red teaming
Adversarial testing that attacks your own systems to find vulnerabilities before someone else does.
From the episode “Tokenomics Will Wreck Your Margins: The AI Model Routing Workflow That Cuts Spend”Hear it on the podcast1 episode
Learn the language of AI-native founders
Every week: the new terms, tools, and workflows founders are using, straight from the podcast.
Related terms in AI Fundamentals
Prompt injectionAn attack that hides malicious instructions in input, like a web page or email, to trick an LLM into ignoring its rules or taking unintended actions.RAG (Retrieval-Augmented Generation)A technique where a model first looks up relevant information from documents or databases, then uses it to write a more accurate, up-to-date answer.RationalistsAn online community focused on reasoning and AI risk.Reasoning modelA model built to work through hard problems step by step before answering, trading extra time for better accuracy.Reinforcement learningTraining an AI through trial and error: it takes actions, gets rewards or penalties, and learns which choices lead to better results.Responsible AIThe principles and practices for developing and deploying AI ethically and safely, including fairness, transparency, and accountability.RWKVAn attention-free, linear architecture Eugene co-created, now under the Linux Foundation, designed to lower inference cost.Scaling lawsPredictable relationships showing how model performance improves as you increase model size, training data, and compute.