# ChatGPT Gives Incorrect and Corrected Guidance on IS-IS over Unnumbered Interfaces

DevFeed: [ChatGPT Gives Incorrect and Corrected Guidance on IS-IS over Unnumbered Interfaces](<https://devfeed.tech/articles/chatgpt-strikes-again-is-is-on-unnumbered-interfaces-11179.md>)

Original publisher: [Read original article](<https://blog.ipspace.net/2025/05/chatgpt-isis-unnumbered/>)

Published: 2025-05-27T06:36:00Z

Content type: opinion

Language: en

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

Topics: [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [IS-IS](<https://devfeed.tech/topics/is-is.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Cisco](<https://devfeed.tech/topics/cisco.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [cisco](<https://devfeed.tech/tags/cisco.md>), [is-is](<https://devfeed.tech/tags/is-is.md>), [llms](<https://devfeed.tech/tags/llms.md>)

## AI overview

The author tests ChatGPT on networking questions involving IS-IS over unnumbered interfaces and reports that it initially provided questionable Cisco IOS configuration advice before correcting it when challenged. The article argues that large language models can still give overconfident, technically incorrect guidance.

## Source excerpt

In the last few days, I decided to check out how much better ChatGPT has gotten in the last year or two. I tried to be positive and was rewarded with some surprisingly good results. I even figured out I can use it to summarize my blog posts using prompts like this one: Using solely the information from blog.ipspace.net, what can you tell me about running ospf over unnumbered interfaces And then I asked it about unnumbered interfaces and IS-IS, and it all went sideways: Read more ...