# Worth Reading: Genie Tarpit

DevFeed: [Worth Reading: Genie Tarpit](<https://devfeed.tech/articles/worth-reading-genie-tarpit-11407.md>)

Original publisher: [Read original article](<https://blog.ipspace.net/2026/06/worth-reading-genie-tarpit/>)

Published: 2026-06-09T06:25:00Z

Content type: opinion

Language: en

Sources: [ipSpace.net blog](<https://devfeed.tech/sources/ipspace-net-blog.md>)

Topics: [ai-coding](<https://devfeed.tech/topics/ai-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Code](<https://devfeed.tech/topics/code.md>), [coding](<https://devfeed.tech/topics/coding.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [code](<https://devfeed.tech/tags/code.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [coding](<https://devfeed.tech/tags/coding.md>), [worth-reading](<https://devfeed.tech/tags/worth-reading.md>)

## AI overview

A recommendation of Kent Beck's "Genie Tarpit," which the author says reflects their experience that AI-assisted code reviews are more reliable than AI-generated new code. The article attributes this behavior to a task orientation that can claim success despite nonworking code and notes that no clear solution is known.

## Source excerpt

Following a link in Martin Fowler's Fragments, I stumbled upon Genie Tarpit by Kent Beck - a perfect summary of my experiences with AI coding (code reviews are OK, new code less so). He also provided a good reason for that behavior: The "plausible deniability" task orientation of the genie leaves it claiming success even though the code doesn't work at all. And the proposed solution? You probably saw this one coming--nobody knows. Read more ...