Love your observation about the market opportunity for senior developers to help newbies. I’ve been using cursor for at least months to program in variety of new languages to me. Especially before sonet it frequently got stuck going in circles and I ended up hiring a couch/teacher on Upwork to help me get unstuck. It wasn’t super easy to find someone and I have the market for helping new programmers develops with new marketplaces, service offerings, and tools.
Sure the apps are simple now, but 1) it will get smarter, and 2) it's already good enough to unlock a new software class. I build a bingo card for football for the house in 15 minutes on my phone last night
I doubt that opportunity will be available for senior devs as ai will also be able to answer all those questions. From the next model stage say gpt 5 opus 3.5 lastest the models after that senior devs going to have to focus on how to stay ahead
For me Replit only works when I use Python without any implementation of LLMs APIs - at the moment for me useless - maybe for some basic productivity apps or data visualization - I just waisted 25$ for subscription.
All these tools currently produced by various companies are just novelties and nothing more for people who want to start their programming journey. In my opinion, it's better to understand the basics first to know what these tools actually produce. There are plenty of opinions online where people go on about what they've achieved with tools like Cursor AI or Replit AI. However, from my perspective, Replit AI doesn't stand out in any way and, in fact, is even worse than Cursor AI with Composer. However, in my experience, when dealing with a slightly larger repository-not a huge one, but one with around 150 files with already written code-the attempt to add a new feature that would use the existing logic and previously prepared tools is more frustrating than helpful. Cursor AI supposedly indexes the repository, so why do I have to point out the exact files it should use every time I want to add a new feature to create something with the previously developed tools? Otherwise, it tries to write something itself, and in a much worse way. There's still a long way to go for these models (a much larger context window is needed to really grasp what’s happening in a project) and for the developers who create these tools. Every time, I get caught up in the same thing-posts on X by marketers or people who are being paid for it (because how else to explain that these tools are still so poor), praising how their productivity jumps by 150% when writing in English. When I provide too many files, these tools start to get lost in what they should do. If there's a specific approach to creating services, repositories, DTOs, or utilities in a repository, I would expect such tools to stick to that rather than suggesting their own solutions that deviate significantly from the standards presented in the repository. Once again, I feel disappointed.
sooo . . . . you got paid for this endorsement? There have been at least a dozen online and offline agents for Claude 3.5 like this, replit is not even the best one around.
sooo . . . you assume Nate is taking bribes because he he doesn't happen to know your favorite agent - and you expect him to know about this (according to you) better agent, which you don't even care to name? also, Nate's channel basically just launched - he has 2000 subscribers. why do you assume someone with 2000 subscribers is getting paid to promote products? I'd be a lot more suspicious of channels with 100K+ subscribers. the channels with reach are usually the ones offered (and taking) bribes!
Love your observation about the market opportunity for senior developers to help newbies. I’ve been using cursor for at least months to program in variety of new languages to me. Especially before sonet it frequently got stuck going in circles and I ended up hiring a couch/teacher on Upwork to help me get unstuck. It wasn’t super easy to find someone and I have the market for helping new programmers develops with new marketplaces, service offerings, and tools.
I really think there's billions on the table there
Great video. Thank u man
Glad you liked it!
Hello Nate,
Do you think it could be a good thing to connect Cursor in Replit ? Because, it seems very hard to debug with the Replit Agent
What I'd love to see, and I haven't found anyone who's done it, is a comparison to Claude projects. A lot of the features seem to overlap.
Sonnet 3.5 is under the hood for Cursor I believe, so that would make sense.
I love how your example of replit's supposed broad problem solving scope is a web scraper which is the example in every other AI agent demo
Sure the apps are simple now, but 1) it will get smarter, and 2) it's already good enough to unlock a new software class. I build a bingo card for football for the house in 15 minutes on my phone last night
I doubt that opportunity will be available for senior devs as ai will also be able to answer all those questions. From the next model stage say gpt 5 opus 3.5 lastest the models after that senior devs going to have to focus on how to stay ahead
We will have to see!
I’m so curious if Replit was made using Cursor
No. Replit has been around for years and this is a new feature.
Mike i think they used Github copilot - there are a lot of bugs
Yep Replit is having a moment now but they're not new
For me Replit only works when I use Python without any implementation of LLMs APIs - at the moment for me useless - maybe for some basic productivity apps or data visualization - I just waisted 25$ for subscription.
All these tools currently produced by various companies are just novelties and nothing more for people who want to start their programming journey. In my opinion, it's better to understand the basics first to know what these tools actually produce. There are plenty of opinions online where people go on about what they've achieved with tools like Cursor AI or Replit AI. However, from my perspective, Replit AI doesn't stand out in any way and, in fact, is even worse than Cursor AI with Composer.
However, in my experience, when dealing with a slightly larger repository-not a huge one, but one with around 150 files with already written code-the attempt to add a new feature that would use the existing logic and previously prepared tools is more frustrating than helpful. Cursor AI supposedly indexes the repository, so why do I have to point out the exact files it should use every time I want to add a new feature to create something with the previously developed tools? Otherwise, it tries to write something itself, and in a much worse way.
There's still a long way to go for these models (a much larger context window is needed to really grasp what’s happening in a project) and for the developers who create these tools. Every time, I get caught up in the same thing-posts on X by marketers or people who are being paid for it (because how else to explain that these tools are still so poor), praising how their productivity jumps by 150% when writing in English. When I provide too many files, these tools start to get lost in what they should do. If there's a specific approach to creating services, repositories, DTOs, or utilities in a repository, I would expect such tools to stick to that rather than suggesting their own solutions that deviate significantly from the standards presented in the repository. Once again, I feel disappointed.
I think a more accurate take is our old programming priors are breaking down and don't work well right now and we have to reorient.
sooo . . . . you got paid for this endorsement?
There have been at least a dozen online and offline agents for Claude 3.5 like this, replit is not even the best one around.
lmao if by paid you mean I paid them and had fun with the tool sure but not this is not paid
@@NateBJones The bigger you get, the haters go +1.
sooo . . . you assume Nate is taking bribes because he he doesn't happen to know your favorite agent - and you expect him to know about this (according to you) better agent, which you don't even care to name?
also, Nate's channel basically just launched - he has 2000 subscribers. why do you assume someone with 2000 subscribers is getting paid to promote products? I'd be a lot more suspicious of channels with 100K+ subscribers. the channels with reach are usually the ones offered (and taking) bribes!
A dozen that allow you to deploy?
@@e.x5264 still not helpful. 🤷♂️