Guides from Sentient Cloud

Longer, plain-language pages on the questions this site exists to answer.

How language models predict text A language model predicts what comes next in a piece of text. That one skill, trained on a lot of writing, covers many tasks.
Training versus inference Training is how a model gets its weights. Inference is how it uses them. The two have different costs, and both spend energy.
What an AI agent is An agent is a model given a goal and some tools, then run in a loop: act, look at the result, act again. Here is what that loop is, and where it fails.
What is a neural network? A neural network is layers of simple units that learn from examples. Here is what that means, and what it does not mean, in plain language.
What these systems cannot do Today's language models and agents are useful, and they have hard limits. Here is a clear list of things they do not reliably do.