Machine Learning
Most RAG Hallucinations Are Retrieval Failures: How the Retrieval Brick Decides What the Model Can Invent
2 weeks ago
Most RAG Hallucinations Are Retrieval Failures: How the Retrieval Brick Decides What the Model Can Invent
a confident wrong answer, the instinct is to reach for the generation knobs: a stricter prompt, a bigger model, a…
How Do I Make Sure My Math Work Is Not Eaten By AI
2 weeks ago
How Do I Make Sure My Math Work Is Not Eaten By AI
someone at work brings up a version of this question: will AI take my job? I will admit that I…
25 years of the invention of visual search
2 weeks ago
25 years of the invention of visual search
Both updates build on 25 years of innovation to make the world's visual information more quickly accessible and usable. To…
A Gentle Introduction to Autoencoders & Hidden Space
2 weeks ago
A Gentle Introduction to Autoencoders & Hidden Space
Hard computation is a well-known problem in various ML algorithms today, especially when generative AI is applied to text, images,…
Kubiza Malini Ngempela Ukuqalisa I-LLM Yasendaweni? (Ama-Euro ngeMillion Tokens, Kukaliwe)
2 weeks ago
Kubiza Malini Ngempela Ukuqalisa I-LLM Yasendaweni? (Ama-Euro ngeMillion Tokens, Kukaliwe)
ngakho empeleni kumahhala.” Sengikushilo lokho, mhlawumbe ukushilo lokho, futhi wuhlobo lwesimangalo oluzwakala luyiqiniso kuze kube yilapho umuntu esilinganisa. Ngakho ngayilinganisa.…
Pydantic + OpenAI: The Cleanest Way to Get Systematic Results from LLMs
2 weeks ago
Pydantic + OpenAI: The Cleanest Way to Get Systematic Results from LLMs
In my latest post on edited output, there are three main ways to get machine-readable answers in LLM. Those are…
Agent RAG: Let Agent Search
2 weeks ago
Agent RAG: Let Agent Search
the constructive application is the RAG application. The recipe is simple: chunk, embed, extract, and turn. It looks clean on…
Context Rot: Why Claude Code Sessions Decay, and How to Govern Them
2 weeks ago
Context Rot: Why Claude Code Sessions Decay, and How to Govern Them
The context window is a core feature of every frontier model. Measured in tokens, it is typically made up of…
Building Models in Two Worlds: From Latent Constructs to Behavioral Signals
2 weeks ago
Building Models in Two Worlds: From Latent Constructs to Behavioral Signals
Two response variables that look identical and aren’t , the thing I was trying to predict was a survey answer:…
The Three Dimensions of Custom Agentic Alignment: Purpose, Principles and Practices
2 weeks ago
The Three Dimensions of Custom Agentic Alignment: Purpose, Principles and Practices
are rapidly moving from experimental prototypes to embedded actors across industries, government operations, and everyday digital workflows. Their accelerating capabilities,…