# Code: science and production

DevFeed: [Code: science and production](<https://devfeed.tech/articles/code-science-and-production-36730.md>)

Original publisher: [Read original article](<https://shostack.org/blog/code-science-and-production/>)

Author: Adam

Published: 2020-05-26T00:00:00Z

Content type: opinion

Language: en

Sources: [Shostack & Friends Blog](<https://devfeed.tech/sources/shostack-friends-blog.md>)

Topics: [Code](<https://devfeed.tech/topics/code.md>), [Software](<https://devfeed.tech/topics/software.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Maintainability](<https://devfeed.tech/topics/maintainability.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [developers](<https://devfeed.tech/tags/developers.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [maintainability](<https://devfeed.tech/tags/maintainability.md>), [security](<https://devfeed.tech/tags/security.md>), [software](<https://devfeed.tech/tags/software.md>), [tests](<https://devfeed.tech/tags/tests.md>)

## AI overview

The article discusses the differences between exploratory and production code, especially in scientific and machine-learning work. It argues that converting exploratory code into production-quality software is costly and considers tradeoffs involving testing, documentation, maintainability, error checking, and security.

## Source excerpt

Phil Bull presents an interesting, generally convincing, argument in 'Why you can ignore reviews of scientific code by commercial software developers', with a couple of exceptions.