I was part of the first cohort and I will be taking the course again. SolveIt has a unique take on how to best work with AI that helps produce better end products and helps you learn along the way. The platform is tailored to implementing the methodology taught in the course but the lessons can be taken when working in other AI tools to obtain better results.
I had access to GitHub Copilot as a student in early 2022 while learning Haskell and immediately realised that it would hinder my learning if I didn't turn it off and implicitly follow this understand, plan, execute, reflect loop.
AI products like Cursor have the notion of an 'autonomy slider' [1] that can fortunately be turned all the way down (disable Cursor Tab) but relying on this discipline seems fickle when with the right agentic loops [2] and context engineering, thousands of lines of code can be churned out with minimal supervision.
I've considered always working on two projects over a long timespan, one with no AI assistance, possibly in a separate IDE like Zed, and one in Vibe Kanban (my current daily driver) but this feels like an inefficient proxy to accelerating this four step learning loop with a tool like solveit.
Since the solveit product isn't released and seemingly isn't competing with solutions, is there an opportunity to convey how AI product developers should be thinking about amplifying their users and keeping them in the learning loop?
So far, I've seen Claude Code's Learning output style [3], and also ChatGPT's study mode but in these cases, the only product change is a prompt and solveit is more than that.
I was part of the first SolveIt course cohort and have signed up for the second one too. SolveIt and its methodology really changed how I approach programming and problem solving with AI. It gives you a collaborative partner that helps you think through problems without just handing you answers. You still do the hard thinking, but you are never completely stuck. It has also allowed me to tackle tasks, ideas and experiments that I had previously put to the side knowing they would have taken too much time and effort to explore.
Although it can take more steps and iterations than other tools, that is part of the difference, they are more considered and thought through steps. It makes me more productive overall. The ability to edit the conversation and work in short steps lets you create better context, together with sharing your thought process and building genuine understanding that is useful in the future.
It is refreshing to find an approach that makes me better rather than just faster at producing code without full understanding of it. I find it jarring to use chat with other LLMs now and that typical code completion can be frustrating, that is how different it is.
I'm sure I'm not the only one confused by this, but can you give details on why you decided that a course was necessary to learn this new way of working with AI?
Maybe it's more of a alpha thing, but with millions using chatbots every day, was it not possible to develop a UI?
It's not just about adoption, who has the time to spend 5 weeks learning a new tool? Particularly when you're competing with the existing tools?
The course is about a methodology, not a product. It's the ideas Eric Ries and I have been working on for decades. 5 weeks is a crash course that can only touch on the ideas. And it covers learning data structures and algorithms, foundations of web programming, system administration, startup creating, and much more.
It's really a rapid "how do to <x> the solveit way" for a variety of x. Each of those x is likely to become a full course in the future.
(We actually built the tool for ourselves, and only decided to make it publicly available when we realised how much it's helping us. We're a PBC so our mission is not entirely financial. We're not trying to compete with existing tools, but provide an alternative direction.)
We made the tool, and that will eventually be available on its own. But the method requires some discipline and 'unlearning'. It's very hard to show someone an AI tool and not have them treat it just like ChatGPT/Claude/... - that's the part that takes the time, and having a community of people working through different examples and case studies together is a lot more motivating for this than just staring at an empty prompt box :)
That's a good explanation, but I think the expectation when someone says they are "launching something" that is an antidote to AI fatigue, it may be better to say it's a course and a methodology. You aren't launching a tool.
I think if you give it a try, you'll be surprised. It is a course and a tool and a way of thinking. We often struggle to find concise language to describe something that is fundamentally new. Maybe after you've tried it, you'll be able to help us explain it better.
I'm deep in category creation myself, so I know exactly where you're at.
But as I'm sure you know, you need to get the language right in order to create the desire to try.
I don't personally have AI fatigue. Nor do I have the time to spend 5 weeks taking a course to use a tool that I don't have enough context for.
Being in Australia timezone wise, and launching a start-up doesn't help.
This doesn't mean in any way that I'm not rooting for your success. But as you know, the language of understanding something new is a long iterative process.
I thought it might be helpful to post a link to one of my favorite writeups from the beta cohort for solveit (last year). It's written by Chris Thomas:
Being among the first 1000 people to experience SolveIt has felt like witnessing the early days of a significant shift in how we work with AI. As someone who is a seasoned programmer, I have seen many programming paradigms and the advance of AI coding tools. What makes SolveIt different is not just another tool or framework - it is a fundamental rethinking of the human-AI relationship.
As I look at my experience with SolveIt, I think this is a better more sustainable approach to AI-assisted development. The current trend of ever more powerful models generating ever larger blocks of code feels unsustainable. SolveIt offers a different path. By maintaining human agency, working in comprehensible increments and building genuine understanding at each step, it creates a positive feedback loop where both human and AI capabilities grow stronger over time. This represents a partnership model that builds competence over time rather than creating dependence.
The implications extend far beyond programming. Whether I am implementing computer vision algorithms, exploring culinary science, or writing technical articles - the same principles apply. Small steps, continuous understanding, iterative refinement and always keeping the human as the agent in the process.
Hey everyone, Eric Ries here. solveit is the AI environment I personally have been using every day for months, not just for code but for writing and research, too.
it’s solved all the problems and frustrations I’ve had with both vibecoding and the limitations of the chatbot interface for doing deep work that requires concentration + the ability to understand the artifacts you are producing
and, as a special bonus, people in this course will get a sneak preview of the new book I’m working on. we’re going to use it both to teach some of the concepts from it (on how to create mission-driven long-term companies) and how to use solveit for longform writing projects
happy to answer any questions here, for folks that want to learn more,
(For those that don't recognise the name, Eric is the creator of The Lean Startup, and also founded the Long Term Stock Exchange. He's the co-founder of Answer.AI, which has built the solveit platform, and which fast.ai is now part of.)
Thanks Eric (and Jeremy and Johno). The course details are a bit sparse on the sign-up site. What's the expected time commitment for the course over the 5 weeks? And how useful would the course be if you missed a few of the courses and had to catch up later?
And this prompted me to record a video showing some of my random non-work usage recently, to give a feeling for what the app looks like :) https://youtu.be/Y2B27hdKMMA
Here is a video showing off using solveit for creating a web app. https://youtu.be/DgPr3HVp0eg?t=3120 To reiterate other comments, this is more about the methodology than the tool, but it is fun to see the tool in action too.
As a self taught hobbyist I progressed pretty far in advent of code 2023 until I gave up and less so in 2024 but my approach seems to be close to the one described (if you dig a little deeper into the signup page) or so I imagine. I was disciplined about not asking for help with the problem itself and went to chatgpt for help with components or syntax I needed to build a function I already had in mind (which was closer to the state of the art - especially in 2023 anyway). I think the advent of code problems are really interesting and have enjoyed solving them and watching others solve the ones I couldn’t. They are a fun way to frame the course. However the real value to me is learning how to approach more ambiguous problem spaces. I am definitely interested.
I participated in the first cohort and I'll be doing it again because I enjoyed it so much the first time around. The course focuses on teaching a robust problem solving approach, rather than explicitly teaching people how to program with AI. It's not a dream or a scam! If you digest the course concepts, the takeaways can be put into practice even if you aren't programming directly in SolveIt. But the SolveIt application certainly greases the wheels by making this problem-solving approach easier and fun! My growth as a programmer has been supercharged by what I learned and applied in the past year since taking the first course.
Why does this article not mention what solveit is at all? It talks about what they did, then that they made this tool, then that it's great, but what is it? Watch this video!
No, give me a sentence or two about what it does. I'm not watching a video about a tool while reading a blog post about it because you couldn't be bothered to write a line or two about it.
As someone who participated in the first cohort but is not part of their team, i would say it’s a programming environment for AI assisted literate programming.
It’s like an intelligent notebook. That means you could use this for many different things but at least to me the high order bit is „AI assisted literate programming“
Considering how the folks at answer.ai have been using (successive versions of) it to build this tool itself and judging by student projects and showcases, it definitely goes beyond exploratory. You can build big stuff with it.
Personally I’m using it to learn the whole fastai ecosystem.
That's fair! I guess since it's a new thing that doesn't quite neatly fit in a category, we were perhaps too shy about trying to define it. Also, we really want to focus on the methodology, rather than the platform. But yes, you're right we should explain the platform too. :) I'll have a go here, and will then go and add it to Johno's article.
So basically, you can think of the platform as combining all these: ChatGPT; Jupyter Notebook + nbdev; Bits of vscode/cursor (we embed the same Monaco editor and add similar optional AI and non-AI autocompletion); a VPS (you get your own persistent full VPS running Linux with a URL you can share for public running applications); Claude Code (all the same tools are available); a persistent terminal.
Then there's some bits added that don't exist elsewhere AFAIK: something like MCP, but way simpler, where any Python function can be instantly used as an AI tool; the ability to refer directly to any live Python variable in AI context (but optional, so it doesn't eat up your context window); full metaprogramming of the environment (you can through code or AI tools modify the environment itself or the dialog); context editing (you can -- and should -- directly edit AI responses instead of tell the AI it's wrong); collaborative notebook coding (multiple people can edit the dialog, run code, etc, and all see live updates).
The combination of these things is rather different (and IMO better!) than the sum of its parts, but hopefully this helps a bit?
This is such a steep price tag. I loved what Jeremy Howard put up on fast.ai and respect the heck out of his team, but I've seen too many people scammed by online courses that sell a dream. This one seems to be selling a dream as well.
I'll be purchasing the course to try it out but I think my concern is not a one-off thing.
I participated in the first batch and am not a shill, look through my comment history.
The dismissive comments here pain me as Ive seen them work hard on this over the last year as they integrated many of our feature requests and built out the platform. I’ve also had time to let the ideas sink in.
You definitely cant hang back and expect some magic ai to do all the work for you.
I also cant say „you will definitely benefit“ since everybody is difft.
But i can honestly say it‘s the real deal, no ifs and buts.
I'd urge folks here to atleast go through https://www.youtube.com/watch?v=DgPr3HVp0eg before jumping to conclusions about what SolveIt or this course is about. Its the polar opposite of vibe coding IMO.
I watched the video and it’s basically a “Jupyter notebook” type of app where you can type code and chat with the AI.
It’s nice cause it makes the interaction more dynamic and iterative. Honestly the “changing the answer” thing is something I always did on LM Studio when I wanted to change course. Definitely better than the limited interfaces of chatbots today, but I’m not sure it’s “revolutionary” by any means.
Still, it’s something I’d prefer until someone finds a better way to interact with LLMs. The ability to add stuff, remove stuff, move things around etc. probably help a lot when you’re creating something. It better matches the state of our minds. Also I appreciate the “using AI for learning instead of producing slop or — like many posts I’ve seen before — optimized spam.
I’m not sure what’s up with the course though. Seems more like a way to try to monetize something that wouldn’t be monetizable in any other way.
In fact I’m sure someone more knowledgeable than me could just create a Jupyter Notebook plugin that would replicate most of what this is?
Hi all - Jeremy Howard from Answer.AI here. Really excited to share with you all what we've learned over the past year about how to work with AI in a way that's entirely human-centered.
Whilst most folks seem focused on how to remove humans from the loop entirely and make AIs do all the work, we've concentrated 100% on how to make humans part of the loop in a way that makes us more and more capable and engaged.
I've enjoyed building and using our tool, "solveit", for the last year, and do basically all my coding, writing, reading, research, etc in it nowadays. I use small fast iterative steps and work to maximize my learning at each step.
I took the 1st course and really loved it. I got a little distracted by focusing on building web apps with fasthtml(which was covered in the course), but I think the practices that are tough are extremely important for anyone using LLMs on a daily basis. I am really excited to learn about all the new features in solveIt.
As the post mentions, a year ago we did a trial of it, and have been working with that group of 1000 users since then.
The course is about a methodology, not a product. It's the ideas Eric Ries and I have been working on for decades. 5 weeks is a crash course that can only touch on the ideas. And it covers learning data structures and algorithms, foundations of web programming, system administration, startup creating, and much more.
It's really a rapid "how do to <x> the solveit way" for a variety of x. Each of those x is likely to become a full course in the future.
You obviously see a ton of value here, but a bunch of industry professionals still aren’t getting it. This is a communication problem. Y’all probably should consider investing in a (different?) marketing or communications consultant.
It's not a course on how to learn how to use the product. It's a course on how to think and solve problems, which makes you more effective in using the platform.
Without the intent of hijacking whatever it is you are trying to achieve: I've found the best antidote to the AI-fatigue is to rely less on it. There is no way I am going to spend my day, or my employees day for that matter in reviewing thousands of LoC of bad AI-slop. In my teams we've dialed it back to just consulting mode and asking suggestions,e.g. replacement for good old search, because once you ask the GenAI to write a few thousands of LoC for you, you're also abandoning a lot architecture decisions (which you then have to figure out ad-hoc again, when you do the review of the slop, or at the latest when you notice the "smart" tool has yet again put a secret in plaintext or something similar). So yeah, if you have the so-called AI-fatigue, just use less of the so-called AI.
Absolutely right! Although I've found AI great for learning. It doesn't write my code for me, or my prose, or my devops scripts, but it's part of the process of me learning as I write them.
I couldn't love more all the intentions behind this, but I have no idea what it is. Why would someone who already knows and loves Polya and iterative programming and human-centered technology... use this? What is the value add?
but, honestly, I hope that list makes you see why we had a hard time figuring out how to summarize what solveit is. For example, I use it for research and writing all the time, but you'd have a hard time seeing why a notebook plus a private VPS would do much for that use case. But it does! Having a general-purpose computing environment is just very, very useful in a wide range of situations.
I personally think it is as a platform as a tool for thought. Building your solution and your knowledge at the same time by leaning on what LLMs do well, while avoiding the common pitfalls.
One thing I loved about the first solveit course was how create the community is. It goes back to fast.ai too, but everyone is super kind, smart, and has diverse backgrounds.
I read most of this before understanding that I wasn't reading about some new agent or IDE or something, I was reading a sales pitch for a coding course for would-be vibe coders, with AI training wheels in the form of ... a dialog box to talk to an LLM.
I should have noticed the camp counselor / cultish / tedx vibes, throwin around REPL and feedback loops. I feel that it's somewhat misleading to present this as some amazing self-building software or server platform here, and bury the lede that what's being sold is an experimental tutoring method. It's almost like those "I built an AI agent that builds AI agents" posts, only instead of selling the sixty lines of python, it's selling a set of lectures that goes with them.
Can you provide some links? Because I see that Eric Ries has a resume on Wikipedia that mainly highlights his book, "The Lean Startup." I see that he was adjacent to some dot-com-bubble-era startups. I see he has a handsome photo. I don't see where he actually founded a successful startup; if anything, reading his resume makes me think he stopped coding and discovered a more successful career in selling promises to young people that his methodologies would turn them into successful entrepreneurs. To me, that does sound like a grift. I mean, why bother doing the actual work of starting a startup, coding and solving lots of problems, when you can present yourself as a guru in how startups work, right? Smart. Also, shady.
Apparently he also runs a stock exchange with two companies on it. And a lot of "core principles". Lol. Speaking as someone who coded and ran the first Bitcoin casino and was around a lot of early crypto bullshit in the nascent years of BTC when lots of dudes like this had crazy plans to commoditize it all sorts of ways, this is juvenile boiler room stuff that would have been laughed out of the Bitcoin Business Association Skype chat in 2010. (And yes, dread pirate roberts was there for a sec, and the general level of dialog was a far sight more intelligent than this dreck).
I got hell-banned here for criticizing PG for running this very site basically to achieve the same grift - to form a cult of young people who'd worship him in exchange for pie in the sky promises that they would become successful startup founders. But to be fair, PG has both actual experience and a ton of investment capital to prove it, so his cult followers have at least some chance of receiving an investment (or a gift, if you think kissing his ass is the essential requirement) that will catapult them into another echelon.
These guys are just living the mantra of "fake it til you make it." This reminds me of the $500 I spent when I turned 21 to take a bartending class for two weeks. Loads of fun. End result: There was one job on their board for graduees, for a bar that had been closed for a couple years. Turned out the best way to become a bartender was to learn on the job.
Turned out that was also the best way to become a software engineer.
I apologise folks that we did a bad job of explaining exactly what we're launching! My bad. :( I've added this to the top of the article now -- I hope this does a better job of explaining things:
----
*tldr from Jeremy:* You can now sign up for Solveit, which a course in how to solve problems (including coding, writing, sysadmin, and research) using fast short iterations, and also provides a platform that makes this approach easier and more effective. The course shows how to use AI in small doses to help learn as you build, but doesn't rely on AI at all -- you can totally avoid AI if you prefer. The approach we teach is based on decades of research and practice from Eric Ries and I, the founders of Answer.AI. It's basically the opposite of "vibe coding"; it's all about small steps, deep understanding, and deep reflection. We wrote the platform because we didn't find anything else sufficient for doing work the "solveit way", so we made something for ourselves, and then decided to make it available more widely. You can follow the approach without using our platform, although it won't be as smooth an experience.
The platform combines elements of all these: ChatGPT; Jupyter Notebook + nbdev; Bits of vscode/cursor (we embed the same Monaco editor and add similar optional AI and non-AI autocompletion); a VPS (you get your own persistent full VPS running Linux with a URL you can share for public running applications); Claude Code (all the same tools are available); a persistent terminal. Then there's some bits added that don't exist elsewhere AFAIK: something like MCP, but way simpler, where any Python function can be instantly used as an AI tool; the ability to refer directly to any live Python variable in AI context (but optional, so it doesn't eat up your context window); full metaprogramming of the environment (you can through code or AI tools modify the environment itself or the dialog); context editing (you can -- and should -- directly edit AI responses instead of tell the AI it's wrong); collaborative notebook coding (multiple people can edit the dialog, run code, etc, and all see live updates).
A great course and helps with learning proactively and not reactively. Important in this age of ai. I was part of cohort 1 and have enrolled for the next one.
The AI is an integral part of the platform. My impression from reading the reviews on their website is that you won’t go anywhere using Solveit if you don’t let the LLM give you feedback.
I've been using SolveIt for about a month and going through the previous cohort content. It's really hard to not to try to vomit out solutions and to go about something in a methodical way. It makes your work visible, maintainable and usable by others (and frankly yourself). It takes a lot of practice, but it is very much intangible and always in the process of becoming. If you want to focus on solving pretty much any problem, and a path to using AI effectively in any endeavor, then this is a really fulfilling path. You will find that there is more magic in AI than you suspect. Many praises to Jeremy and Johno and the SolveIt team. But don't take my word for it. I'm a fresh convert. Go check it out for yourself. It is subtle and requires nuance, so not for everyone.
I was part of the first cohort and I will be taking the course again. SolveIt has a unique take on how to best work with AI that helps produce better end products and helps you learn along the way. The platform is tailored to implementing the methodology taught in the course but the lessons can be taken when working in other AI tools to obtain better results.
I had access to GitHub Copilot as a student in early 2022 while learning Haskell and immediately realised that it would hinder my learning if I didn't turn it off and implicitly follow this understand, plan, execute, reflect loop.
AI products like Cursor have the notion of an 'autonomy slider' [1] that can fortunately be turned all the way down (disable Cursor Tab) but relying on this discipline seems fickle when with the right agentic loops [2] and context engineering, thousands of lines of code can be churned out with minimal supervision.
I've considered always working on two projects over a long timespan, one with no AI assistance, possibly in a separate IDE like Zed, and one in Vibe Kanban (my current daily driver) but this feels like an inefficient proxy to accelerating this four step learning loop with a tool like solveit.
Since the solveit product isn't released and seemingly isn't competing with solutions, is there an opportunity to convey how AI product developers should be thinking about amplifying their users and keeping them in the learning loop?
So far, I've seen Claude Code's Learning output style [3], and also ChatGPT's study mode but in these cases, the only product change is a prompt and solveit is more than that.
[1] https://www.latent.space/i/166191505/part-a-autonomy-sliders [2] https://simonwillison.net/2025/Sep/30/designing-agentic-loop... [3] https://docs.claude.com/en/docs/claude-code/output-styles#bu...
I was part of the first SolveIt course cohort and have signed up for the second one too. SolveIt and its methodology really changed how I approach programming and problem solving with AI. It gives you a collaborative partner that helps you think through problems without just handing you answers. You still do the hard thinking, but you are never completely stuck. It has also allowed me to tackle tasks, ideas and experiments that I had previously put to the side knowing they would have taken too much time and effort to explore.
Although it can take more steps and iterations than other tools, that is part of the difference, they are more considered and thought through steps. It makes me more productive overall. The ability to edit the conversation and work in short steps lets you create better context, together with sharing your thought process and building genuine understanding that is useful in the future.
It is refreshing to find an approach that makes me better rather than just faster at producing code without full understanding of it. I find it jarring to use chat with other LLMs now and that typical code completion can be frustrating, that is how different it is.
I'm sure I'm not the only one confused by this, but can you give details on why you decided that a course was necessary to learn this new way of working with AI?
Maybe it's more of a alpha thing, but with millions using chatbots every day, was it not possible to develop a UI?
It's not just about adoption, who has the time to spend 5 weeks learning a new tool? Particularly when you're competing with the existing tools?
The course is about a methodology, not a product. It's the ideas Eric Ries and I have been working on for decades. 5 weeks is a crash course that can only touch on the ideas. And it covers learning data structures and algorithms, foundations of web programming, system administration, startup creating, and much more.
It's really a rapid "how do to <x> the solveit way" for a variety of x. Each of those x is likely to become a full course in the future.
(We actually built the tool for ourselves, and only decided to make it publicly available when we realised how much it's helping us. We're a PBC so our mission is not entirely financial. We're not trying to compete with existing tools, but provide an alternative direction.)
We made the tool, and that will eventually be available on its own. But the method requires some discipline and 'unlearning'. It's very hard to show someone an AI tool and not have them treat it just like ChatGPT/Claude/... - that's the part that takes the time, and having a community of people working through different examples and case studies together is a lot more motivating for this than just staring at an empty prompt box :)
That's a good explanation, but I think the expectation when someone says they are "launching something" that is an antidote to AI fatigue, it may be better to say it's a course and a methodology. You aren't launching a tool.
I think if you give it a try, you'll be surprised. It is a course and a tool and a way of thinking. We often struggle to find concise language to describe something that is fundamentally new. Maybe after you've tried it, you'll be able to help us explain it better.
I'm deep in category creation myself, so I know exactly where you're at.
But as I'm sure you know, you need to get the language right in order to create the desire to try.
I don't personally have AI fatigue. Nor do I have the time to spend 5 weeks taking a course to use a tool that I don't have enough context for.
Being in Australia timezone wise, and launching a start-up doesn't help.
This doesn't mean in any way that I'm not rooting for your success. But as you know, the language of understanding something new is a long iterative process.
I thought it might be helpful to post a link to one of my favorite writeups from the beta cohort for solveit (last year). It's written by Chris Thomas:
https://christhomas.co.uk/blog/2025/09/24/the-human-is-the-a...
a few quotes/excerpts:
Hey everyone, Eric Ries here. solveit is the AI environment I personally have been using every day for months, not just for code but for writing and research, too.
it’s solved all the problems and frustrations I’ve had with both vibecoding and the limitations of the chatbot interface for doing deep work that requires concentration + the ability to understand the artifacts you are producing
and, as a special bonus, people in this course will get a sneak preview of the new book I’m working on. we’re going to use it both to teach some of the concepts from it (on how to create mission-driven long-term companies) and how to use solveit for longform writing projects
happy to answer any questions here, for folks that want to learn more,
Eric
(For those that don't recognise the name, Eric is the creator of The Lean Startup, and also founded the Long Term Stock Exchange. He's the co-founder of Answer.AI, which has built the solveit platform, and which fast.ai is now part of.)
Oops that should say "which fast.ai is now part of". s/not/now/
I fixed it :)
Thanks Eric (and Jeremy and Johno). The course details are a bit sparse on the sign-up site. What's the expected time commitment for the course over the 5 weeks? And how useful would the course be if you missed a few of the courses and had to catch up later?
do you have a video of someone using it?
And this prompted me to record a video showing some of my random non-work usage recently, to give a feeling for what the app looks like :) https://youtu.be/Y2B27hdKMMA
Here is a video showing off using solveit for creating a web app. https://youtu.be/DgPr3HVp0eg?t=3120 To reiterate other comments, this is more about the methodology than the tool, but it is fun to see the tool in action too.
Thanks Erik - I've added that video to the article now.! :)
We also showed it as part of Hamel's course: https://x.com/HamelHusain/status/1956514524628127875 (https://www.youtube.com/watch?v=DgPr3HVp0eg) which is a longer example of the tool in action
Latent Space just released an interview about Solveit: https://www.youtube.com/watch?v=01ybLOH1fnU
I loved this interview, I can't wait to learn more about the tool use aspect.
As a self taught hobbyist I progressed pretty far in advent of code 2023 until I gave up and less so in 2024 but my approach seems to be close to the one described (if you dig a little deeper into the signup page) or so I imagine. I was disciplined about not asking for help with the problem itself and went to chatgpt for help with components or syntax I needed to build a function I already had in mind (which was closer to the state of the art - especially in 2023 anyway). I think the advent of code problems are really interesting and have enjoyed solving them and watching others solve the ones I couldn’t. They are a fun way to frame the course. However the real value to me is learning how to approach more ambiguous problem spaces. I am definitely interested.
I participated in the first cohort and I'll be doing it again because I enjoyed it so much the first time around. The course focuses on teaching a robust problem solving approach, rather than explicitly teaching people how to program with AI. It's not a dream or a scam! If you digest the course concepts, the takeaways can be put into practice even if you aren't programming directly in SolveIt. But the SolveIt application certainly greases the wheels by making this problem-solving approach easier and fun! My growth as a programmer has been supercharged by what I learned and applied in the past year since taking the first course.
Why does this article not mention what solveit is at all? It talks about what they did, then that they made this tool, then that it's great, but what is it? Watch this video!
No, give me a sentence or two about what it does. I'm not watching a video about a tool while reading a blog post about it because you couldn't be bothered to write a line or two about it.
As someone who participated in the first cohort but is not part of their team, i would say it’s a programming environment for AI assisted literate programming.
It’s like an intelligent notebook. That means you could use this for many different things but at least to me the high order bit is „AI assisted literate programming“
I see, thank you. Is this more of an exploratory programming tool, then? A Jupyter notebook with AI features?
Considering how the folks at answer.ai have been using (successive versions of) it to build this tool itself and judging by student projects and showcases, it definitely goes beyond exploratory. You can build big stuff with it.
Personally I’m using it to learn the whole fastai ecosystem.
I'll give it a shot, thanks!
That's fair! I guess since it's a new thing that doesn't quite neatly fit in a category, we were perhaps too shy about trying to define it. Also, we really want to focus on the methodology, rather than the platform. But yes, you're right we should explain the platform too. :) I'll have a go here, and will then go and add it to Johno's article.
So basically, you can think of the platform as combining all these: ChatGPT; Jupyter Notebook + nbdev; Bits of vscode/cursor (we embed the same Monaco editor and add similar optional AI and non-AI autocompletion); a VPS (you get your own persistent full VPS running Linux with a URL you can share for public running applications); Claude Code (all the same tools are available); a persistent terminal.
Then there's some bits added that don't exist elsewhere AFAIK: something like MCP, but way simpler, where any Python function can be instantly used as an AI tool; the ability to refer directly to any live Python variable in AI context (but optional, so it doesn't eat up your context window); full metaprogramming of the environment (you can through code or AI tools modify the environment itself or the dialog); context editing (you can -- and should -- directly edit AI responses instead of tell the AI it's wrong); collaborative notebook coding (multiple people can edit the dialog, run code, etc, and all see live updates).
The combination of these things is rather different (and IMO better!) than the sum of its parts, but hopefully this helps a bit?
That helps a lot, thanks!
This is such a steep price tag. I loved what Jeremy Howard put up on fast.ai and respect the heck out of his team, but I've seen too many people scammed by online courses that sell a dream. This one seems to be selling a dream as well.
I'll be purchasing the course to try it out but I think my concern is not a one-off thing.
I participated in the first batch and am not a shill, look through my comment history.
The dismissive comments here pain me as Ive seen them work hard on this over the last year as they integrated many of our feature requests and built out the platform. I’ve also had time to let the ideas sink in.
You definitely cant hang back and expect some magic ai to do all the work for you.
I also cant say „you will definitely benefit“ since everybody is difft.
But i can honestly say it‘s the real deal, no ifs and buts.
Is this an ad?
I'd say the fact that I'm unable to show purchase intention without being accused of being a shill proves my point.
I was unaware that you had a point.
I'd urge folks here to atleast go through https://www.youtube.com/watch?v=DgPr3HVp0eg before jumping to conclusions about what SolveIt or this course is about. Its the polar opposite of vibe coding IMO.
I watched the video and it’s basically a “Jupyter notebook” type of app where you can type code and chat with the AI.
It’s nice cause it makes the interaction more dynamic and iterative. Honestly the “changing the answer” thing is something I always did on LM Studio when I wanted to change course. Definitely better than the limited interfaces of chatbots today, but I’m not sure it’s “revolutionary” by any means.
Still, it’s something I’d prefer until someone finds a better way to interact with LLMs. The ability to add stuff, remove stuff, move things around etc. probably help a lot when you’re creating something. It better matches the state of our minds. Also I appreciate the “using AI for learning instead of producing slop or — like many posts I’ve seen before — optimized spam.
I’m not sure what’s up with the course though. Seems more like a way to try to monetize something that wouldn’t be monetizable in any other way.
In fact I’m sure someone more knowledgeable than me could just create a Jupyter Notebook plugin that would replicate most of what this is?
Hi all - Jeremy Howard from Answer.AI here. Really excited to share with you all what we've learned over the past year about how to work with AI in a way that's entirely human-centered.
Whilst most folks seem focused on how to remove humans from the loop entirely and make AIs do all the work, we've concentrated 100% on how to make humans part of the loop in a way that makes us more and more capable and engaged.
I've enjoyed building and using our tool, "solveit", for the last year, and do basically all my coding, writing, reading, research, etc in it nowadays. I use small fast iterative steps and work to maximize my learning at each step.
I'm slightly confused. From your comment I expected an AI chat tool, but solveit appears to be more a class?
It's both! We built a new platform designed to be a good place for using the approach we've designed. So it's a course, plus access to the platform.
Sorry it is a bit confusing tbh!
No worries, keen to try out your approach.
I took the 1st course and really loved it. I got a little distracted by focusing on building web apps with fasthtml(which was covered in the course), but I think the practices that are tough are extremely important for anyone using LLMs on a daily basis. I am really excited to learn about all the new features in solveIt.
Ironically AI would've done a better job at summarizing what is this about than thousands of words of this post.
dang. thought this was a service for people tired of reading about AI.
in a way, it is
I see a $400 price tag on a five week course. If it takes 5 weeks to learn how to use your product, I am skeptical that it has legs.
Side note: supposedly this is the first cohort of this course, so how do you already have testimonials?
As the post mentions, a year ago we did a trial of it, and have been working with that group of 1000 users since then.
The course is about a methodology, not a product. It's the ideas Eric Ries and I have been working on for decades. 5 weeks is a crash course that can only touch on the ideas. And it covers learning data structures and algorithms, foundations of web programming, system administration, startup creating, and much more.
It's really a rapid "how do to <x> the solveit way" for a variety of x. Each of those x is likely to become a full course in the future.
You obviously see a ton of value here, but a bunch of industry professionals still aren’t getting it. This is a communication problem. Y’all probably should consider investing in a (different?) marketing or communications consultant.
It's not a course on how to learn how to use the product. It's a course on how to think and solve problems, which makes you more effective in using the platform.
I guess I was lucky. I'm old enough that this was taught to me in school for free. That was way back in the day before it was outlawed.
Without the intent of hijacking whatever it is you are trying to achieve: I've found the best antidote to the AI-fatigue is to rely less on it. There is no way I am going to spend my day, or my employees day for that matter in reviewing thousands of LoC of bad AI-slop. In my teams we've dialed it back to just consulting mode and asking suggestions,e.g. replacement for good old search, because once you ask the GenAI to write a few thousands of LoC for you, you're also abandoning a lot architecture decisions (which you then have to figure out ad-hoc again, when you do the review of the slop, or at the latest when you notice the "smart" tool has yet again put a secret in plaintext or something similar). So yeah, if you have the so-called AI-fatigue, just use less of the so-called AI.
Absolutely right! Although I've found AI great for learning. It doesn't write my code for me, or my prose, or my devops scripts, but it's part of the process of me learning as I write them.
I couldn't love more all the intentions behind this, but I have no idea what it is. Why would someone who already knows and loves Polya and iterative programming and human-centered technology... use this? What is the value add?
Jeremy attempted a summary here: https://news.ycombinator.com/item?id=45456928
but, honestly, I hope that list makes you see why we had a hard time figuring out how to summarize what solveit is. For example, I use it for research and writing all the time, but you'd have a hard time seeing why a notebook plus a private VPS would do much for that use case. But it does! Having a general-purpose computing environment is just very, very useful in a wide range of situations.
I personally think it is as a platform as a tool for thought. Building your solution and your knowledge at the same time by leaning on what LLMs do well, while avoiding the common pitfalls.
One thing I loved about the first solveit course was how create the community is. It goes back to fast.ai too, but everyone is super kind, smart, and has diverse backgrounds.
We've captured a slice of that on our main site. Testimonials: https://solve.it.com/testimonials Some blog posts: https://solve.it.com/#showcases on the main page
And on of the students even made a project dashboard page showcasing all the things everyone has built! https://solveit-project-showcase.pla.sh/
He even blogged about it : ) https://himalayanhacker.substack.com/p/how-i-built-solve-it-...
I read most of this before understanding that I wasn't reading about some new agent or IDE or something, I was reading a sales pitch for a coding course for would-be vibe coders, with AI training wheels in the form of ... a dialog box to talk to an LLM.
I should have noticed the camp counselor / cultish / tedx vibes, throwin around REPL and feedback loops. I feel that it's somewhat misleading to present this as some amazing self-building software or server platform here, and bury the lede that what's being sold is an experimental tutoring method. It's almost like those "I built an AI agent that builds AI agents" posts, only instead of selling the sixty lines of python, it's selling a set of lectures that goes with them.
In other words, a grift.
Same conclusion.
Maybe you should look a bit more into the folks who made this before dissing their work like this.
I did do that now, and I see a string of similar consultant-like training/course packages. It's a bit like when Deloitte comes by to pitch.
What have they built that impressed you?
I love almost everything they have done, I would highly recommend looking a little deeper.
Can you provide some links? Because I see that Eric Ries has a resume on Wikipedia that mainly highlights his book, "The Lean Startup." I see that he was adjacent to some dot-com-bubble-era startups. I see he has a handsome photo. I don't see where he actually founded a successful startup; if anything, reading his resume makes me think he stopped coding and discovered a more successful career in selling promises to young people that his methodologies would turn them into successful entrepreneurs. To me, that does sound like a grift. I mean, why bother doing the actual work of starting a startup, coding and solving lots of problems, when you can present yourself as a guru in how startups work, right? Smart. Also, shady.
Apparently he also runs a stock exchange with two companies on it. And a lot of "core principles". Lol. Speaking as someone who coded and ran the first Bitcoin casino and was around a lot of early crypto bullshit in the nascent years of BTC when lots of dudes like this had crazy plans to commoditize it all sorts of ways, this is juvenile boiler room stuff that would have been laughed out of the Bitcoin Business Association Skype chat in 2010. (And yes, dread pirate roberts was there for a sec, and the general level of dialog was a far sight more intelligent than this dreck).
I got hell-banned here for criticizing PG for running this very site basically to achieve the same grift - to form a cult of young people who'd worship him in exchange for pie in the sky promises that they would become successful startup founders. But to be fair, PG has both actual experience and a ton of investment capital to prove it, so his cult followers have at least some chance of receiving an investment (or a gift, if you think kissing his ass is the essential requirement) that will catapult them into another echelon.
These guys are just living the mantra of "fake it til you make it." This reminds me of the $500 I spent when I turned 21 to take a bartending class for two weeks. Loads of fun. End result: There was one job on their board for graduees, for a bar that had been closed for a couple years. Turned out the best way to become a bartender was to learn on the job.
Turned out that was also the best way to become a software engineer.
Totally
I apologise folks that we did a bad job of explaining exactly what we're launching! My bad. :( I've added this to the top of the article now -- I hope this does a better job of explaining things:
----
*tldr from Jeremy:* You can now sign up for Solveit, which a course in how to solve problems (including coding, writing, sysadmin, and research) using fast short iterations, and also provides a platform that makes this approach easier and more effective. The course shows how to use AI in small doses to help learn as you build, but doesn't rely on AI at all -- you can totally avoid AI if you prefer. The approach we teach is based on decades of research and practice from Eric Ries and I, the founders of Answer.AI. It's basically the opposite of "vibe coding"; it's all about small steps, deep understanding, and deep reflection. We wrote the platform because we didn't find anything else sufficient for doing work the "solveit way", so we made something for ourselves, and then decided to make it available more widely. You can follow the approach without using our platform, although it won't be as smooth an experience.
The platform combines elements of all these: ChatGPT; Jupyter Notebook + nbdev; Bits of vscode/cursor (we embed the same Monaco editor and add similar optional AI and non-AI autocompletion); a VPS (you get your own persistent full VPS running Linux with a URL you can share for public running applications); Claude Code (all the same tools are available); a persistent terminal. Then there's some bits added that don't exist elsewhere AFAIK: something like MCP, but way simpler, where any Python function can be instantly used as an AI tool; the ability to refer directly to any live Python variable in AI context (but optional, so it doesn't eat up your context window); full metaprogramming of the environment (you can through code or AI tools modify the environment itself or the dialog); context editing (you can -- and should -- directly edit AI responses instead of tell the AI it's wrong); collaborative notebook coding (multiple people can edit the dialog, run code, etc, and all see live updates).
A great course and helps with learning proactively and not reactively. Important in this age of ai. I was part of cohort 1 and have enrolled for the next one.
So the antidote to AI fatigue is... more AI?
No, the first example shown doesn't use AI at all. The AI is an optional helper in the process, if needed/wanted.
The AI is an integral part of the platform. My impression from reading the reviews on their website is that you won’t go anywhere using Solveit if you don’t let the LLM give you feedback.
Sigh. I agree with the parent poster’s sentiment.
as someone who uses solveit all the time, this has not been my experience
I find I use the AI less and less the more I use SolveIt tbh
no definitely not the case.
This post and whole comment section is like a coordinated advertisement
I've been using SolveIt for about a month and going through the previous cohort content. It's really hard to not to try to vomit out solutions and to go about something in a methodical way. It makes your work visible, maintainable and usable by others (and frankly yourself). It takes a lot of practice, but it is very much intangible and always in the process of becoming. If you want to focus on solving pretty much any problem, and a path to using AI effectively in any endeavor, then this is a really fulfilling path. You will find that there is more magic in AI than you suspect. Many praises to Jeremy and Johno and the SolveIt team. But don't take my word for it. I'm a fresh convert. Go check it out for yourself. It is subtle and requires nuance, so not for everyone.
who tf would pay money for this??
I will and did.
fast.ai (some of the authors of this) was transformative for me, and the community was super nice. Cannot recommend looking into this highly enough.