Jev Is Not an LLM  🔗 **Source:** [Jev Is Not an LLM](https://www.youtube.com/watch?v=PNbbMi2h9VA) [00:00:00] A new model has just been released that's changing the way we use AI. Built by one of the inventors of chat GPT and the mind behind the popular post trading technique RLHF, Jeff by Type Safe AI is on average 200 times faster and 400 times cheaper than every frontier model, but it wasn't designed to generate text. No chat, no code, no sentences. Despite this, people have used it to self-drive a Tesla in real time, search through a database with natural language, and play four characters in Smash Bros quicker than a human. How? Well, Jeff is what Type Safe call a system one model inspired by this book from Daniel [00:00:39] Kahneman that splits human thinking into two systems. System one for fast, intuitive, and automatic decisions, and system two for slow and effortful decisions. Jeff is built to be system one. You hand it some state like instructions or a row of data, a list of questions with multiple predefined answers, and Jeff hands back the [music] typed answers with probabilities. And that's essentially it. Jeff has [music] three question types: choice to select an option from a defined set, score for rating content against descriptive levels, and null when the answer is yes or no, returning probabilities and not a verdict. I'll tell you later on why Jeff [00:01:20] is more than a glorified if statement, but because it can understand languages [music] just as well as any frontier model, I can write code like this with a state section that has a condition with [music] the text "What a breathtaking sunrise." I'll have some questions here, and I'm using the choice type for the question, which is "What color is the sky?" And these are the options I've given for colors. So, if I run the code, Jeff comes back with a choice of salmon and a 0.89 confidence number. I can change the code to include another choice question, which will give me a choice of dawn because it's a sunrise. [00:01:56] But if I change the text here to stars between the clouds, Jeff changes the sky color to indigo and the time of day to night because it understands the text and knows that stars only appear in the evening. From here, we can add different logic based on these decisions or even pass it to an LLM to write a human-readable response. We could also add objects to each criteria to give Jeff more context to base its answers on, but also to have clearer boundaries between options. Now, if we try to do the same thing with a model like Claude, we can set the different options in an array and we'll have to use something like Zod to define the types. And it [00:02:38] also returns salmon with a lower confidence level. But, and here's the interesting part, it actually cost us output tokens to generate this output. And remember, with other models, output tokens cost money, but with Jeff, it's completely free. Comparing Jeff with Claude 3 Sonnet 5, we can see input tokens from Jeff are a fraction of the cost of Sonnet and output tokens on Jeff are completely free. And even with GPT-5 6 Luna, Jeff has much cheaper input tokens. So, this can be used to do some really cool things. Here's another example. I need to find the Hamilton book on this site, but there's no search bar. So, instead of me going through [00:03:19] each section one by one or the most likely section to find the books, I can use Jeff and Firecrawl to do so. So, Firecrawl will do an initial scrape of the page and hands the categories to Jeff. Jeff will pick the most likely categories that the book will be in, and then Firecrawl will scrape those pages, give them to Jeff, and Jeff will find the right book based on our criteria. So, in our code, I've given Jeff a goal. Firecrawl is going to scrape those pages, and Jeff is going to take those pages and use it to make the right decision based on the goal we set earlier. So, running this code, Jeff has ranked music the highest since Hamilton [00:03:59] is a musical, Firecrawl has scraped all the books for music and it hasn't found it, so it's gone to non-fiction and it's taken all the pages from non-fiction and it goes through all 53 pages until it finds the right one over here, which for some reason was in the non-fiction section. Now, I know Firecrawl has a map feature to give Jeff all the pages that already exist from the sitemap and it could choose the best one, but this is a cool demo to show for sites that don't have a sitemap. But, what's so revolutionary about Jeff? Haven't computer games had this sort of technology for about 30 years? Well, yes and no, because although game AI also [00:04:35] has defined outputs like Jeff, a developer has to write the logic and every rule in advance. With Jeff, you don't have to write any of that. You just show it what's going on and it picks the best option. So, although offline AI will always be faster than Jeff, which has to make calls to the network, what's even crazy is that we're having this comparison in the first place. The fact that Jeff is fast enough to play these games in real time and even multiple games in parallel is mind-blowing. So, that's a quick overview of Jeff, the first system one model from Typesafe. I know it seems simple from the outset, but it opens up [00:05:12] a whole new world of possibilities and I can't wait to see what new and existing tools use this amazing model for. If you want to know more about Firecrawl or even sign up to it, you can use this code to get 500 extra credits. And if you want to know how I was able to play Doom inside of Claude's code while it completed a task using a new feature called Claude Mods, then check out the next video., Jev Is Not an LLM, Firecrawl, 01m32js042bex18yvf38pt6e30.