What Should Your Kid Learn When AI Does the Heavy Lifting?. You watch your kid type a half-finished sentence into an AI chatbot and come back with a paragraph that scans better than yours did at their age. Do they still need the slow work? ai-2026 parenting-ai ai-ready-kids foundations-vs-tools kids-and-ai You watch your kid type …
What Should Your Kid Learn When AI Does the Heavy Lifting? · Hanh D. Brown Read More »
, local LLMs are an attractive option. They allow us to keep our sensitive data and reduce our dependency on cloud APIs. However, running the model locally is only the first step. In a practical application, the local LLM is usually part of a larger workflow. This means its responses often need to be consumed …
How to Implement Structured Output with Local LLMs Read More »
Physical AI Trains Robots in a Simulated World First. The chips built to make games look real became the engines of AI. Now they train machines to move, in a simulated world that runs millions of practice trials before lunch. ai-2026 physical-ai robotics simulation-training ai-energy The chips built to make video games look real became …
Physical AI Trains Robots in a Simulated World First · Hanh D. Brown Read More »
Contents# Small But Powerful# Why Small Language Models Deserve More Attention# Understanding SmolLM3’s Architecture# Setting Up Your Environment# Loading SmolLM3 and Running Your First Inference# Building a Multilingual Support Ticket Router# Adding Tool Calling to SmolLM3# Fine-Tuning SmolLM3 on Domain Data# Conclusion # Small But Powerful Running a 70B model in production can be expensive, slow, and, for many tasks, unnecessary. If you’re building …
Small Language Models with Hugging Face transformers Library + smolLM3 Read More »
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 »
Contents# Crawling, Not Scraping# 1. Olostep# 2. Firecrawl# 3. ScrapeGraphAI# 4. Scrapling# 5. Crawl4AI# 6. Scrapy# 7. Crawlee# Final Thoughts # 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 …
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 …
