Blog | ZacTax

Jul 15, 2026

Revisiting our 2025 Southern California sales tax forecast

We revisit our 2025 Southern California sales tax forecast a year later and find that an honest range beat a confident guess (and that averaging our two models would have beaten either one alone).

california forecasting

Apr 22, 2026

Same Chart, Different Story: Confidence vs. Prediction Intervals

Most forecasts include a range, but not all ranges answer the same question. This post breaks down the difference between confidence and prediction intervals, and why it matters for real-world city decisions.

forecasting

Apr 15, 2026

Forecasting in the fog: why ranges beat point estimates

If your forecast is just one number, it’s probably telling an incomplete story. Here’s how prediction intervals add the context city leaders actually need to plan ahead.

forecasting

Apr 4, 2026

The power of a good prompt

A vague prompt gets unpredictable results. A specific one gets reliable results. Here's how to write prompts that actually work, using techniques you already know from managing people.

ai language models

Apr 1, 2026

How can we prevent LLMs from hallucinating?

LLM hallucination is manageable, but not by waiting for smarter models. The real solution is giving the model less room to guess. Here are four techniques that make AI outputs dramatically more reliable.

ai language models

Mar 4, 2026

What is a context window?

LLMs can only hold so much information at once. Understanding context windows helps explain why long conversations sometimes go off the rails.

ai language models

Feb 25, 2026

Why do LLMs hallucinate?

LLMs can generate confident, detailed responses that are completely wrong. Understanding why this happens helps you use these tools effectively.

ai language models

Feb 18, 2026

How do LLMs generate text?

When ChatGPT responds to your prompt, it's not retrieving an answer from a database. It's predicting the next word, one token at a time, based on probability.

ai language models