Bradley - When I use ChatGPT through my browser, I can upload a PDF of a technical paper and the bot reads it instantly and communicates at near perfection to convert equations in the paper to Wolfram code. The problem is that after a bit the OpenAI link wants me to upgrade at a cost of $? or it shuts me off until tomorrow. Since I have a ChatGPT API key I presume that is what they want. I bought the Wolfram notebook assistant and assumed it - or a Chat Notebook - would provide the same functionality. Apparently not. In the Chat notebook I have selected OpenAI as the model and input my API Key. Even with that I am told to Import the pdf as plain text into the notebook. I can do that but the LaTex functionality is lost in the Plaintext conversion. Division signs are omitted and subscripts are ignored so differentials and exponents are not right unless I do a HUGE amount of tedious editing one character at a time. It seems like there is a LOOOOOONG step between what OpenAI offers directly and the version of it that comes through the notebook.

I would much prefer to go through Wolfram for these things. If I am doing something wrong, please advise. But the Wolfram Chat bot seems to be well below the OpenAI equivalent. I am happy to pay $20 a month to one or the other of you but it does not seem to make sense to do both since OpenAI will supply everything I need without the Notebook Assistant.

David - Thanks for that. And I get it, the bot can't be perfect. That is why they call it ARTIFICIAL intelligence. Whatever the situation I ALWAYS double- and triple-check for errors. It is just that the ChatGPT version is both very easy and very accurate. The window has the familiar clip icon Not only can one upload the paper but if you want to add data to test the theory the paper expresses, it is just another paper-clip-icon click and the data is uploaded!!!. This saves HOURS of tedious typing. These are ministerial, have been around for years, so it is hard to understand when Wolfram does not allow/adopt similar time-saving convenience.

It is not associated with the plan. It is a limit of the Model. Whenever you are carrying on a conversation with the LLM, for example, in a Chatbook, it sends the full history of the conversation to the model. At some point, the number of tokens that are being sent to the model exceeds the limit of the model. You can see the various context limits of the OpenAI models here OpenAI Models

From your messages I am guessing that you are using one of the older gpt-4 models which have a total context limit of 8192 tokens

I'm curious whether the Notebook Assistant subscription applies to both PC's that I am able to run under my Wolfram Premium Plus subscription?

I'm a bit disappointed that my Wolfram Premium Plus subscription does not include Notebook Assistant. That means I have to have multiple subscriptions. Not only that, if I want to have an AI service on my phone and on my PC's, but I also have to have an additional subscription, in my case XAi/Grok. Grok isn't supported in the list of AI services on the Wolfram desktop app. No Chat Notebooks for Grok apparently? I've been a Wolfram customer since at least version 3...

No. Grok is XAi (from Elon Musk). Groq is from a distinctly different vendor. I'm surprised this is not well known by now.

I'm not sure how I can directly make suggestions to the developers (other than ones that may read this forum on an uncertain frequency). I would think that a platform on the level of XAi would be on their radar without users needing to make suggestions. Even the just announced DeepSeek from the CCP is in the list you posted. You and Bradley have Wolfram Research in your profiles, maybe you could pass it along?

Hi David. I can confirm that the Wolfram Notebook Assistant + LLM Kit will work on both of your computers where you have Wolfram desktop products installed. It's access is tied to your Wolfram ID, not your activation codes, so it will work on any computer where you sign in.

Bradley -- I just found out about this and, late on a Saturday before Christmas, I excitedly purchased a year's supply. I have a license number for the product but do not find anywhere to register it. Chat enabled notebooks seem to work as usual. Should I imaging there is enough AI in it to connect my subscription to my license number. That brings up the question: Can I use it on my laptop with my Home License I get from Premier Support?

You won't to buy tokens from OpenAI for either level of the Notebook Assistant + LLM Kit product. Instead of using third-party providers, you connect directly to our server and we take care of the rest.

You're correct that we've set the plan limits based on non-industrial strength usage. And yes, you have it right that if you hit those limits, you can still buy Wolfram Service Credits which will allow you to keep going.

Bradley I bought the Notebook and it doesn't work. I have been a user since 2,0 at full commercial level and Stephen's minions have asked me to do book reviews for him on Amazon (and I did one on his book on CHATGPT). I have pursued this with the alleged "Premier Service" but what you don't realise is the commercial stuff I disclosed to them. I suggest you get in touch with them. But basically I think Wolfram has lost control of quality control - please pass that on to Stephen (the Premier service people can give you my background ) I would like to see this work but I am not hopeful. Peter

Update: NA wouldn't properly install on my Surface book. The 413 meg index file just did not want to properly extract and I messages which have an active link to GitHub - this had a real beta test vibe to it. After the 3rd attempt the index search term file downloaded and I was able to query. My frustration was doubled because 14.1 will not install on my Imac despite multiple attempts and this is the subject of a ticket.

Hello Héctor, thanks for the question.

Yes, I can confirm that all of the Notebook Assistant and LLM Kit features and capabilities are included in both the Essentials and Pro subscriptions. The difference between the two subscriptions is only in the usage limits. The Pro subscription has double the usage limit of the Essentials subscription.

Hope that helps!

Wow. My first thought was that the Wolfram Summer School will be dramatically different in 2025. With the Assistant, students can rapidly iterate over a sets of [wholly unexpected] ideas. The overused phrase quantum leap comes to mind...

MIT (and other schools) has held an Integration Bee during IAP for the past 40 years. Maybe MIT's new Schwarzman College of Computing could hold an annual IAP Computation Bee where competitors create a set of computations/visualizations in a set of 3-minute challenges. Creative genius arises from highly-constrained competitions, and participants could could definitely "stand on the shoulders" of their fellow competitors.

The Wolfram Demonstrations Project was launched with Mathematica 6 in 2007 (I found an announcement in the MathWorld Headline News). The Demonstrations Project continues to be an excellent tool for both accessing computational principles and ways to approach computational ideas. At the same time, the Demonstrations Project doesn't sparkle. It looks inwards, but it doesn't pull people from other communities with its vast dazzling capabilities. It also doesn't reflect the vast increase in computational capability available today: multi-core architectures with embedded GPUs and NPUs.

The Wolfram Demonstrations Project could be augmented with the

Wolfram Compelling Computations Project (WCCP).

The WCCP would be a curated list of computations. Each would be introduced by a 4K video; they would be dazzling computations. The computational parts would be available by Computable Document Format files downloadable (and playable) in the Wolfram Player App. The curated notebooks playing in this environment would be an open invitation for students, researchers, and businessmen to leap into the world of AI-generated computation. To borrow from the Cupertino fruit company's marketing, it would be demonstrations of Wolfram Intelligence.

We lack the tools to solve today's problems; we certainly lack the tools to thrive in our complex environment. If there is a "right" way to think about such problems, we don't seem to be thinking that way now.The team at Wolfram Research has made a vast leap to help bridge that gap today. Thank you.

One question I didn't see Stephen address: what impact will the Notebook Assistant have on Wolfram Research's own software development?

The LLM Kit functionality is already available in the cloud. With the subscription you can use LLMFunction and Chat Notebooks in the cloud without configuring any third-party providers.

For Notebook Assistant functionality in the cloud, we make the same advanced computational AI available through Chat Notebooks as long as you're using Wolfram as the LLM Provider. You can ask it the same sort of questions, though it will be using only the current notebook as context. This is available now and we'll also be giving these interfaces more attention in the near future.

Great to hear from you, @John ! If you stumble on some neat examples - please share :-)

There was a bug which I reported to the developers and I believe they have pushed out an update that should fix this. If you continue to have this issue, you should contact technical support.

You are welcome. It was something close to my heart because internally I was the first person to run across this :-). And the developers were very responsive in getting it fixed as quickly as possible.

Impossible not to enjoy the dinosaur story from Stephen :-) A quote from https://wolfr.am/NotebookAssistant

And that reminds me of the very first time I ever saw a computer in real life. It was 1969 and I was 9 years old (and the computer was an IBM mainframe). The person who was showing me the computer asked me: “So what do you want to compute?” I really had no idea at that time “what one might compute”. Rather lamely I said “the weight of a dinosaur”. So, 55 years later, let’s try that again:

You shouldn't have any problem accessing our services from Hong Kong. We aren't restricting access there from our side. We also checked and someone in Hong Kong is currently able to reach our systems.