# LLMs and UUIDs
**URL:** https://discourse.julialang.org/t/llms-and-uuids/115217
**Category:** Offtopic
**Created:** [June 5, 2024, 8:22am UTC](https://discourse.julialang.org/t/llms-and-uuids/115217 "2024-06-05T08:22:03Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@abraemer](https://discourse.julialang.org/u/abraemer)
#### Post date: [June 5, 2024, 8:22am UTC](https://discourse.julialang.org/t/llms-and-uuids/115217/1 "2024-06-05T08:22:03Z")
Continuing the discussion from [DrWatson Common Code as Module Issue](https://discourse.julialang.org/t/drwatson-common-code-as-module-issue/115203/3):
> [@DrWatson Common Code as Module Issue](https://discourse.julialang.org/t/drwatson-common-code-as-module-issue/115203/3):
>
> I was just wondering how likely this exact UUID will now be reproduced by some AI or another. Probably not very likely, but I just imagined ChatGPT going around recommending people to use this UUID with it’s typical “trust me bro” attitude 😁
This prompted me to ask ChatGPT for some UUIDs and it happily “generated” 6 for me. All of them where valid UUIDs and none of them turned anything up in a Google search. So apparently ChatGPT is able to generate UUIDs in principle. Ofc the next question is: Are these random enough? So is it a good idea to use ChatGPT in practice to generate UUIDs? 😃 (yes I know it is a horribly _inefficient_ way of generating them…)
Does anybody know about research in that direction? I.e. how random are the responses of LLMs when asked for some random output?
Funnily enough I also asked it to give me 5 UUIDs that are _already in use_ and the first 2 of the 5 I got are actually widely used:
- `550e8400-e29b-41d4-a716-446655440000` is apparently a default example of an UUID, used in a few documentations and interestingly enough also the name of some file in the [Apache Accumolo](https://github.com/apache/accumulo/blob/main/server/tserver/src/test/resources/walog-from-14/550e8400-e29b-41d4-a716-446655440000) project
- `123e4567-e89b-12d3-a456-426614174000` is used as an example in the [Wikipedia article on UUIDs](https://en.wikipedia.org/wiki/Universally_unique_identifier)
- I could not find anything for the other 3 UUIDs (but they where valid UUIDs)
---
### Author:  [@Tortar](https://discourse.julialang.org/u/Tortar)
#### Post date: [June 5, 2024, 11:59am UTC](https://discourse.julialang.org/t/llms-and-uuids/115217/2 "2024-06-05T11:59:25Z")
As I would expect, it works poorly, this is the prompt I used
> generate 100 uniformly random integers from a range starting from 3128728 to 3128738 extreme included, without using Python, just generate them
Probably we need more samples to be sure but the sample it provided as an occurence count of
```julia
3128735 => 10
3128736 => 9
3128731 => 9
3128738 => 9
3128728 => 9
3128729 => 8
3128733 => 9
3128734 => 9
3128732 => 9
3128730 => 10
3128737 => 9
```
which is very unlikely
---
### Author:  [@Datseris](https://discourse.julialang.org/u/Datseris)
#### Post date: [June 5, 2024, 12:17pm UTC](https://discourse.julialang.org/t/llms-and-uuids/115217/3 "2024-06-05T12:17:11Z")
> [@Tortar](#):
>
> which is very unlikely
hahahahha this would be the numbers you’d get if you ask someone that just started with math, like elementary school or something. They are as random as 7 is a random number between 1 and 10 😃
---
### Author:  [@Jay\_Patel](https://discourse.julialang.org/u/Jay_Patel)
#### Post date: [July 10, 2025, 11:10am UTC](https://discourse.julialang.org/t/llms-and-uuids/115217/4 "2025-07-10T11:10:49Z")
In my code for some reason I had to use UUIDs, apparently it is bad at generating UUIDs. I got to know this when I received a duplicate key error and that’s when I realised that it is generating the same UUIDs that it already generated
---
### Author:  [@Salmon](https://discourse.julialang.org/u/Salmon)
#### Post date: [July 16, 2025, 8:06am UTC](https://discourse.julialang.org/t/llms-and-uuids/115217/5 "2025-07-16T08:06:55Z")
> [@Tortar](#):
>
> which is very unlikely
