Continual Learning Makes AI Remember Your Team’s Work. The smartest model is still a stranger to your company. Continual learning is the bet that the next gain is not a smarter stranger, but a model that has learned you. continual-learning ai-memory fine-tuning rag model-weights The smartest model in the world is still a stranger to …
Continual Learning Makes AI Remember Your Team’s Work · Hanh D. Brown Read More »
scored 94.3% accuracy. I went back over the terminal output and the confusion matrix more than once. They agreed every time. The number went into my README and onto my CV. It was also wrong. Not by a rounding error, either. The honest figure was 69%. No one caught this for me. It only came …
My Fall-Detection Model Scored 94%, and It Was Lying to Me Read More »
AI Infrastructure Runs on Light, Not Just More Chips. The model you talk to is the tip of the iceberg. Under it sit energy, chips, and miles of light-carrying optics that have to be built somewhere. ai-infrastructure optical-interconnect silicon-photonics ai-factory reindustrialization The model you talk to is the tip of the iceberg. Under the water …
AI Infrastructure Runs on Light, Not Just More Chips · Hanh D. Brown Read More »
# Crawling, Not Scraping People often confuse web scraping with web crawling, but they are not the same thing. Web scraping usually means extracting content from a specific page. You give the tool a URL, and it returns the content from that page in a cleaner format. Web crawling goes further. You give the tool …
AI Agents Point to a Society of Specialists, Not One AGI. A language model answers you. An agent goes and does the thing. The moment it can act, and hand work to other agents, the question stops being how clever it is. ai-agents human-in-the-loop prompt-injection cognitive-monoculture agi A language model answers your question. An agent …
AI Agents Point to a Society of Specialists, Not One AGI · Hanh D. Brown Read More »
pipeline needs the document’s table of contents: retrieval scopes by section, and the chunker cuts on heading boundaries instead of mid-sentence. But some documents don’t have one. A paper exported straight from LaTeX has no native outline and no printed contents page, so there is no toc_df for the pipeline to read. The headings are …
The Real Skill in Building With AI Is Writing the Brief. There is a job now where the whole task is describing to a machine what to build, and the person doing it has never written code. The craft did not vanish. It moved. ai-tools clarity context-window product-judgment taste There is a job now where …
The Real Skill in Building With AI Is Writing the Brief · Hanh D. Brown Read More »
# Dealing With Inference Latency As large language models (LLMs) move from research prototypes into production, engineering teams run into a hard truth: building an intelligent model is only half the battle. Serving that model to users in real time is a different engineering challenge entirely. In generative AI, inference is the phase where a …
7 Approaches to Reduce Inference Latency in Your LLM Workflows Read More »
One Answer, Fifteen Models: How an AI Agent Works at Scale. Ask a production agent one question and a stopwatch starts. Two seconds. In that window it will run more models than most people think exist in the whole system. ai-agents reliability voice-ai agent-architecture outcome-pricing Ask a production agent one question and a stopwatch starts. …
Our newest music generation model, Lyria 3.5, delivers significant advancements across musicality, lyrics, and vocal quality, empowering you to craft richer tracks. We’re rolling it out today in Google Flow Music, where we want to help you create songs you love, with creative control. Here’s what’s new: Improved musicality: Create richer, more complex melodic structures …
