We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
Analysis Summary
Worth Noting
Positive elements
- The video offers a practical look at how LLMs can be integrated into a REPL environment for data analysis and recreational mathematics without fully automating away the logic.
Be Aware
Cautionary elements
- The framing of the tool as an 'anti-replacement' solution is a marketing narrative designed to appeal to developers' professional identity.
Influence Dimensions
How are these scored?About this analysis
Knowing about these techniques makes them visible, not powerless. The ones that work best on you are the ones that match beliefs you already hold.
This analysis is a tool for your own thinking — what you do with it is up to you.
Related content covering similar topics.
Transcript
Hello everyone, Jonno here. With the announcement of our new Solve It course, uh people asking what what is Solvent the app? What is this all about? I thought I should show a few of the cases where I've used it outside of work recently just to give you a feel for what Solit looks like. Um the kinds of things that it's ideally suited for um and what you can do. So Solit is kind of like a dialogue between you, you can put notes to yourself. It's also a place to execute code, right? It's a a Jupiter style ripple environment. Um everything is live. So you can see if I've declared a variable um that now exists and I can modify that right and and and follow um what's going on. And it's also a dialogue between you and the computer. So for example, you can uh any Python tool that you can use, you can give that to solve it as a tool. Um and it can interact with the code that you've written, variables that you've defined. Um and yeah, it's all interacting in that same environment. So you can see here it just added to that same variable. um it's able to you know tell us how things work, explain things. Um so some of the use cases um you know scraping data from a site um you can see here like I'm doing a lot of the work myself uh exploring around testing things out but then I'm also able to just hand it like hey here's the content of a page. Could you help me pull out the pieces of information that I'm interested in? Um exploring models so loading up um little models to do bits of ML research on. Again, really great to be able to just interact, explore, or poke at things. And then also, if you hit a roadblock, like at some point something's not working or or you're you're unsure what's going on, being able to ask the AI like, "Hey, you know, how might I uh check that everything's on the right device anytime you need that assistant." Um, yeah, exploring, in this case, um, some recreational maths, you know, is watching a YouTube video. Um, and then again like doing a lot of the stuff myself because it's just fun to have a a computational playground as it were to to test that ideas, but then also being able to ask it to, for example, use the search tool, tell me if I'm on the right track. Uh, it's able to give me um, you know, fancy names to put to to the concepts that's going on. Um, and also for things like, you know, in this case, um, yeah, exploring questions that I have and writing things like the uh, the plotting code. I don't I don't need to to do the um the plotting myself. if I'm more interested in the in the solving, but it's really cool to then have something that can say, "Oh, well, here you go. Here's your uh your fancy mapplot lib um output, right? That's not the uh the end goal for me, but it's nice to have this AI co-worker buddy." Um yeah, so I use this for all sorts of things. I use it when I'm curious whether or not AI can do something to pull together some data and send that as an eval. I use it for um hopping out like in this case I've got a friend who's a civil engineer um analyzing some data loading a file poking at it getting info from the AI how might I pull out the relevant bits you know could it write the regular expression for me thank you very much and then um importantly being able to validate at every step okay these are the lines I'm interested in can I do the convex hull yes it can tell me how to do the convex hull great I just at the bottom yes it can tell me how to get that um so it's very much a back and forth between you between the computer that's executing the code and between the AI Um, so yeah, those are just like some recent dialogues I had open. Um, I hope that elucidates a little bit about how we use solvent as a tool and some of the things it can do. Um, it does feel like a different way of coding to um, anyone who's used to the offload everything to the AI, but it also feels like a very familiar and obvious way of coding if you're at all uh, into the um, you know, the way we used to teach in fast AI, right? The sort of iterative exploratory programming with notebooks and MBDEV. Uh and for most people this it's like why are you describing this as anything new? This is just how good code is code is to do things in small incremental pieces that you understand. Um but yeah it's exciting to build a tool that tries to focus on that in an age where a lot of tools are focused on human replacement. Um so I hope you find that interesting. Uh if you want to come check out a course where we'll be covering how to use this tool and this approach for all sorts of things um check out the new solit course how to solve it with code. Uh but if you're just interested in the tool once that course is complete hopefully we'll be opening up just um kind of pay as you go subscriptions to to access it to use our you know instances in the cloud and our AI. Um but yeah uh otherwise you can take these ideas and you can apply them anywhere. So uh yeah I just hope you get some encouragement from this to keep on playing with code and working at your craft. Thanks for watching.
Video description
To get access to our next course, which includes access to the Solveit platform, go to: https://solve.it.com/