Stories by dbreunig

DeepSeek Is a Rorschach Test Revealing Each's AI Hopes and Fears

The Rise of the Term "Authentic Data" Illustrates AI Anxiety

Your Eval Is More Important Than the Model: Building an Example Eval

The "Cyren" Song: Meta's AI profiles, Character.ai, and other fake humans

A Primer on Synthetic Data: How It's Helping and Shaping LLMs

DSPy Does the Prompting for You

LLMs Hit the Wall: History Reveals How We Went Fast and Why We'll Go Slow

Detecting DuckDB Requests in Your Webapp to Route Them to Remote DBs

Surging crypto prices dampened interest in AI in 2020. Will they do it again?

Transitioning from the attention era to the automation era

It's the UX, Not the LLM: ChatGPT and Perplexity Can Ship a UI Google Can't

Generating Descriptive Weather Reports with LLMs

AI Use Cases: Gods, Interns, & Cogs

AI PCs Aren't Good at AI: The CPU Beats the NPU

The Military Implications of Big vs. Small AI

Building a Crosswalk File with Wikidata, DuckDB, and Ruby Ractors

Conflating Overture Places Using DuckDB, Ollama, Embeddings, and More

What Building Blocks Remains After an AI Collapse?

When is a Minicar as Dangerous as a 3-Ton Truck? (IIHS death-rate data followup)

Ask HN: Who Is OpenAI's O1 For?

1
2
3
4
5
6
7
8
9
10