A Wolfram U Daily Study Group on the intersection between Wolfram Language and LLMs begins on the 10th of November, 2025.
Join me and a cohort of fellow learners to learn about how you can use large language models in the Wolfram environment and—likewise—how you can use Wolfram’s computational intelligence to augment the capabilities of large language models.
This series starts with a discussion about basic back-and-forth chats with LLMs in the notebook environment. The next lessons show how to incorporate LLMs into different workflows and write your own functions that call upon LLMs for input, oftentimes saving a fair amount of time and effort. The series ends with discussions of how to take advantage of Wolfram Language’s computational nature to make LLMs—which are fundamentally stochastic and prone to hallucination—much more robust and reliable, then gives examples of how to combine all of these ideas in order to create single Wolfram Language functions that can call multiple agents and tools simultaneously.
Please feel free to use this thread to collaborate and share ideas, materials and links to other resources with fellow learners.
This is a one week Study Group that will run from November 10 to November 14 at 11AM to 12PM CST.
In Day 1 of the class (Monday), the use of the forward slash key within a chat is discussed. It’s purpose is to enter Wolfram Language in the chat. On my Mac, running 15.7.2 and Wolfram 14.3, When I push the forward slash key (above return), it is not entered. And so nothing happens. Any ideas? I have TextExpander turned off. I can enter forward slash in other applications.
You know, I was flustered this morning by the account issue and called that forward slash when it’s explicitly backslash :). But—as you mention—it is the key above Enter/Return on most keyboards.
My only thought as to why it might not work is an obscure/arcane stylesheet setting. If you open a fresh notebook with cmd+N, immediately open a Chat cell, and type \ in there, does it work? If not, you may want to contact support@wolfram.com because I’m not sure why that would be…
So it does work in a new notebook. Didn’t even restart Wolfram Mathematica. But wont’ work in exiting notebook that I just created yesterday. Very strange.
So think I found problem. If you have dynamic content in the notebook and don’t “approve it” in the banner showing at top of the window, then the forward slash does not work in a chat cell.
Will you include a demo running a local LLM during this course? Is there anything special about accessing an LLM locally, or does that look the same as accessing remotely?
I believe that 2026 will be the first year that local LLM usage becomes widespread. With their A19 Pro and M5 processors, Apple has straightened out a major kink in their architecture. When Apple announced the iPhone 17 models at their September 9 press event, they included a brief discussion of the A19 Pro’s new GPU accelerator in the event:
We have been at the forefront of AI acceleration since we first
introduced the neural engine eight years ago. We later brought
machine-learning accelerators to our CPUs. And while our GPU has
always been great at AI compute, we’re now taking a big step forward,
building neural accelerators into each GPU core, delivering up to
three times the peak GPU compute of A18 Pro. This is MacBook Pro
levels of compute in an iPhone, perfect for GPU-intensive AI
workloads.
That was a bit vague. Fortunately, the “Petar Tech” YT channel explained more in the video Demystifying Apple’s AMX AI accelerator: when and why it outperforms the GPU. In a nutshell, matrix multiplication – a cornerstone of LLM training and token generation – happens atomically in this chip. Historically, the elements of the two matrices being multiplied are fetched from memory multiple times. Petar notes in his video commentary: Because nowadays, the energy needed to transfer data significantly exceeds the energy needed to perform computations on the data. Apparently, NVIDIA has been doing this for several generations on their Tensor Cores; Apple is just catching up on this particular processor feature.
Apple has incorporated the same per-GPU accelerators in its M5 Processors that were released for the low-end MacBook Pro and iPad Pro models this month. In one early test, “Time to First Token” was measured about 3.6x faster than a M4 processor. That baseline M5 processor is limited to 32GB of unified memory, but the “M5 Pro” and “M5 Max” chip computers (both available early 2026) should have up to 128GB of unified memory available. Now that Apple has had time to percolate this change through the years of chip layout and fab, we should be able to run some general-purpose LLMs locally starting soon. All of Apple’s M5 processor computers should be far more attractive than earlier processors for any sort of AI development or usage.
I have registered a OpenAI API key in Preferences / AI Settings / Services. I then select “GPT 4.1 Mini” as the model. My natural language prompt works fine.
But, if I change the model to “GPT-5 Mini”, the same prompt fails with…
The service returned the following error message: Unsupported value: ‘temperature’ does not support 0.7 with this model. Only the default (1) value is supported.
I can fix this problem at Preferences / AI / Settings Services, setting Temperature to 1, and try again. Now it fails with…
The service returned the following error message: Unsupported parameter: ‘presence_penalty’ is not supported with this model.
What to do? All the GPT-5 models fail in the same way.
I reported this two-months ago, and nothing has been done.
PacletInstall["Wolfram/Chatbook", UpdatePacletSites -> True]
```
and fully quit and reopen the app and see if it starts to work? It looks like the bug you're reporting was known about in an older version of the Chatbook paclet that powers all of the Chat cell functionality but was fixed a little while back.
(I'm actually going to just recommend everybody run this at tomorrow's session to head off any issues!)
Hey Arben,
As always, when you teach a class, I sign up.
I thought I had an example here but it was premature.
But sometimes the notebook assistant get’s lost trying to invent functions that don’t exist. (when I am being lazy and trying to get the assistant to write some code for me)
It seems like an inspiration for writing a function that does what it thinks should exist, but what do you do generally when that happens?
Hey Phil! I also watch WWDC ;). I won’t be running anything locally for this series, but maybe in the future. (Though I did just get a new laptop from our IT department earlier this year and won’t be due for an upgrade for a while, so I won’t be benefitting from the M5 improvements! But I really can’t complain.)
As far as whether it’s any different to run things locally, functionally it isn’t. It’s more secure, obviously, and relatedly it’s more private, but the actual functioning of the thing is not really particularly different. The time it takes to send and receive information to/from LLMs is really not that big a component in the total runtime because it’s generally all just text. The extra time taken by network communication may in fact be canceled out by the fact that large companies are already running their setups on specialized hardware, but even if this isn’t quite correct it’s probably close enough as makes no difference. (It’s possible that there are delays based on queuing of their massive numbers of users, though!)
Hi Carl—thank you! This is actually more of a social issue than a technical one, which is not a thing I can say too frequently when asked about error messages :).
Basically, Lena—the image in question—has long been used for image processing examples. However, the image is cropped from a Playboy centerfold and thus many people have thought that maybe different images should be used for testing. You can read about the image and its history at this wikipedia link.
A few updates back, Wolfram decided that we would probably remove Lena as a test image some time in the future, so while the image is currently still available we pop up an “error” message that’s really more of a warning that any code you write that involves the image might not work in the future as the image will eventually not be accessible though ExampleData["TestImage","Lena"].
I think that this context is probably not baked into the models used for Notebook Assistant, and in trying to fix an “error” that wasn’t actually an error it started meandering and getting things wrong. For example, it tried to pull the “Iris” dataset for a machine learning example… but in Wolfram Language, we call that “FisherIris”, not just “Iris”, so it didn’t work. If you run ExampleData["MachineLearning"], you’ll see it in there.
