# IM 805: Doomers, Gloomers, Bloomers, and Zoomers

**URL:** <https://www.twit.community/t/im-805-doomers-gloomers-bloomers-and-zoomers/18020>\
**Category:** Intelligent Machines\
**Tags:** episode\
**Created:** [February 6, 2025, 2:56am UTC](https://www.twit.community/t/im-805-doomers-gloomers-bloomers-and-zoomers/18020 "2025-02-06T02:56:23Z")\
**Posts on this page:** 1\
**Showing post:** 26

<div class="post-metadata">

**Author:** ![floatingbones](https://sea2.discourse-cdn.com/flex020/user_avatar/www.twit.community/floatingbones/32/1557_2.png) [@floatingbones](https://www.twit.community/u/floatingbones)\
**Post date:** [March 2, 2025, 2:59am UTC](https://www.twit.community/t/im-805-doomers-gloomers-bloomers-and-zoomers/18020/26 "2025-03-02T02:59:33Z")

</div>

> [@PHolder](#):
>
> I’ve experienced interactions with ChatGPT where it makes very odd changes unrelated to what it was requested to do. This implies, to me, it doesn’t generally produce repeatable results, and it’s my understanding that the entire concept of “temperature” is basically all about how “creative” it gets.

Intelligent Machines interviewed Stephen Wolfram on Episode 608. Stephen used an analogy between the output of LLMs and building a drywall stone wall. [I quoted it here](https://www.twit.community/t/im-808-stephen-wolfram/18105/2). This analogy gives a great visualization why LLMs create results that are inherently irreproducible.

Interestingly, Stephen’s analogy also makes a compelling case for the superiority of the Wolfram Language and their Notebook Assistant for LLM code generation. You tell in prose what you want the Notebook Assistant to do; it generates Wolfram Language code. At this point, the programmer runs that bit of code and judges its fitness. The programmer either accepts the code, asks the AI to generate code again (perhaps with a different prompt), or manually edits the code to do what the programmer intended.

> [@](#):
>
> If I had a software development team member who appeared to act randomly, I think I would be asking to have them replaced with someone nice and stable, whose output is predictable and it fits in with the rest of the team’s expectations.

If the consistency of a human programmer is like an AI, this would make sense. Stephen is saying that LLMs are fundamentally different in what they’re doing than _any_ human. Furthermore, he thinks the entire LLM code generation procedure is vastly superior for creating production code in the Wolfram Language.

> [@](#):
>
> It may get to the point where you can bring on an AI helper and train them like you would a new team member […]

Again, this is not the mechanism that Stephen is suggesting. He’s suggesting that _each_ member of a team be assisted with LLM code generation, and that the team member individually assimilate the LLM code into the code base. Read his analogy: Wolfram is suggesting this mechanism would generate code where the “rock wall” never gets too “high”. I’m not saying Stephen is correct, but the model he’s proposing is far saner than simply having an AI being “part of the team”.

Wolfram’s approach to LLM code generation may be the best thing going today.

---

_[View the full topic](https://www.twit.community/t/im-805-doomers-gloomers-bloomers-and-zoomers/18020)._