Conceptual
A theoretical, idea-level exploration.
We Trained AI. Now AI Trains Us.
People take on AI's reasoning as their own, and it shapes how they decide next time.
Generative Self-Retrieval: How AI Models Recall Brand Facts From Memory
When an AI answers about your brand from memory, generative self-retrieval decides whether it recalls you correctly or invents a plausible wrong answer.
Clickbait Titles Exploit Attention Through Latent Entities
Clickbait titles function by withholding a latent entity—the subject, reason, process, or outcome—to force a click and resolve an artificial information gap.
Dynamic Visual Layouts
Dynamic visual layout (DVL) is a generative user interface where layouts are created on demand to suit specific queries, shifting the focus from SEO to information.
LLM is a Presentation Layer in AI Search
Large language models act as a presentation layer on top of classic information retrieval. They rely on crawling, indexing, and ranking to prevent hallucinations.
The Latent History of AI Boom
An exploration of how the transition from RNNs to transformers and the discovery of double descent enabled the scaling of large language models like GPT.
Understanding and Control
AI optimization relies on mechanistic interpretability to understand internal neural computations and model steering to actively control model behavior.