Sheela
Sheela
Home
Add
Questions
Thinkers
Claims
People
Concepts
Jargon
Sources
Health
Predictions
Collections
Domain Landscape
Contribute
Review
Dedup
Topic requests
Settings
Help

← Jargon

Jargonsoftware engineering· 2 claims· 2 episodes

unit test

In software, an automated test that checks whether a specific piece of code produces the correct output; here used as an example of measurement data for training models.

As defined in Brendan Foody


Where it comes up · 2
  • Brendan Foody1 claim
  • What's next for AI agentic workflows ft. Andrew Ng of AI Fund1 claim

Most important claims · 2 of 2Search all claims for “unit test” →
  • There are two kinds of data: output/curriculum data the model reads and learns from, and measurement data (rubrics, test questions and answers, unit tests) that lets models attempt a problem many times, score responses, and learn from them—and the second kind is the most valuable.Brendan Foody
  • When an LM's code fails a unit test, prompting the LM to explain why and suggesting changes enables it to generate improved versions (version 3) that work better, creating a feedback loop.What's next for AI agentic workflows ft. Andrew Ng of AI Fund