Insane! Can't believe I'm alive to see AI that can self correct code. Kris is the guy to learn from. I've been a member for a while now and definitely feel that it's worth it!
I wanted to ask you if it's possible to create an entire system with the description of a project and the creation of various files for that project just by using a context window of one million tokens. And after creating this complete system with various functionalities, would it be possible to do something like what you did in this video retroactively, improving the system by fixing bugs and adding new features until it becomes exactly as it was written in the initial project? This would be revolutionary and wonderful, and I'd like to know if you could be the first on TH-cam to do it
Dude, you have access to different llms. You ask them how to do it. Tell it to break it down into steps. Then break down those steps down because it will likely give you steps that to high level. Anything you don't understand, you ask it to explain it to you at 7th grade level. It's more important for you to learn how to use the tools. Tell it what you want to do and ask it if it's possible. Then tell it to give you an example of what it explained. Also you going to have to go into more detail than just a description of a project. You need to go down to user story level for the system to plan. Then even deeper to write the code.
Super cool video on mixing Clause 3 Opus API, ChatGPT 3.5 Turbo, and Python to create a self-correcting AI coding buddy. The walkthrough is insightful and shows some neat tricks.
Thank you for putting the time into figuring this out. It gives me a good idea on how to approach something like this! Keep on giving the great content!
You can make this more efficient by getting the llm to output the code in json. Then deserialise it into a variable. That way we dont need to use a llm to clean the code. { "Code":"" }
Great video, I know the snake game has been one of the tests we all try at some stage, but I have never seen it work first time and then iteratively improve. Awesome!
Wow again Kris! You mentioned in passing about the video or possibly screen shots overread. I think what you did with Elden Ring combined with this style of agents could really open some amazing use cases. Guided education for new software or games of course. But, possibly a broader automation/RPA method for almost any current software available. Examples: Quickbooks to do your taxes, video editing automation, spreadsheet visualizations. Thx!
Kris, thank you for sharing the video. I think the verge website is too easy to crawl (verge is also used in the open Interpreter video). Can you try a more difficult website crawl next time? Thank you
Thanks Kris! You mentioned vision model to deal with screenshots. And the results were not so good. I recommend to try some OCR API. I tested one of them and it worked great even with photos of monitors.
This was going to be my next project but using local LLM's. Anthropic Opus is really good though, so I may have to use it for code writing and self correction. Nice work!
I am curious to know which improvements this code would suggest whilst looking at itself (to have it analyze the code from which it is made) Perhaps it would build a friendly GUI and such .. who knows really. Very useful code solving real issues elegantly! - The compliment! 🖖
cool :) yeah i think a lot of ppl or working on latecy, i guess if you gonna have a consumer facing product it needs to be low latency, ppl dont have any patience and are used to instant responses
I suppose you are right. As an individual, it is harder to reach a wide audience at the same time but you still pull it off! I think you would be happy to know that I have solved the bugs myself and now adding some spice to the sts assistant :) One thing I wanted to ask was - how do i get my assistant to stop listening as soon as I stop talking ? RIght now I press 'ctrl+c' to interrupt and stop recording.
This is really cool , although , it is pretty much AUTOGEn but basic, isnt it? Do you see any advantage using this scope for self correcting AI instead of using something like autogen or crew ai?
In my experience gpt4 is awful when it comes to returning FULL CODE when the code is longer than a few lines. At around 100 lines or before it starts to use placebolders, make up stuff and assume stuff, even things that are clearly defined and described in the code that is provided as context and just plain out hallucinate and break the code.
Nice :D can i play with the code isit on your github? you got a link? i have some code for you its 13 + web apps i made using ai i will swap for your github access i dont really like using discord and yt packages can you do a deal?
Insane! Can't believe I'm alive to see AI that can self correct code.
Kris is the guy to learn from. I've been a member for a while now and definitely feel that it's worth it!
I wanted to ask you if it's possible to create an entire system with the description of a project and the creation of various files for that project just by using a context window of one million tokens. And after creating this complete system with various functionalities, would it be possible to do something like what you did in this video retroactively, improving the system by fixing bugs and adding new features until it becomes exactly as it was written in the initial project? This would be revolutionary and wonderful, and I'd like to know if you could be the first on TH-cam to do it
Dude, you have access to different llms. You ask them how to do it.
Tell it to break it down into steps. Then break down those steps down because it will likely give you steps that to high level. Anything you don't understand, you ask it to explain it to you at 7th grade level. It's more important for you to learn how to use the tools.
Tell it what you want to do and ask it if it's possible. Then tell it to give you an example of what it explained.
Also you going to have to go into more detail than just a description of a project. You need to go down to user story level for the system to plan. Then even deeper to write the code.
Great video Kris!
Super cool video on mixing Clause 3 Opus API, ChatGPT 3.5 Turbo, and Python to create a self-correcting AI coding buddy. The walkthrough is insightful and shows some neat tricks.
Can this produce a full GUI or web interface rather than a simple CLI ?
Always enjoy the content, and continually, learning
thnx :)
I really enjoy all your creative and innovative AI implementations. Thanks for always sharing the code in your member section.
Thank you for putting the time into figuring this out. It gives me a good idea on how to approach something like this! Keep on giving the great content!
You rock, Kris! Thanks for your content and experiments.
thnx :)
Glad i found your YT channel, already learned a bunch, thanks :)
:D
You can make this more efficient by getting the llm to output the code in json. Then deserialise it into a variable. That way we dont need to use a llm to clean the code.
{
"Code":""
}
will def try that again, struggled with this before
Kiris, your videos are always so informative! This one was especially helpful, thank you.
Great video, I know the snake game has been one of the tests we all try at some stage, but I have never seen it work first time and then iteratively improve. Awesome!
You are one of the very few content creators who balance the sensationalism around AI progress with dev based content. Thanks for your efforts
Great video.very informative
Great video! Love the deep dive. Trying it out now!
Thank you Kris! loving the channel more Tutorials and walkthroughs please
Great video Kris. I always learn a lot with your experiments. Thanks!
I;ll definitely try this, it looks quite useful, thanks Kris !
Love this channel
I'm addicted to your channel. Can't wait for the next upload!
Another amazing video!Thank you for putting this together and helping us understand all the processes involved
You're terrific Kriss, keep going with your amazing content, thank you
This is pretty awesome!
thnx :)
Keep up the great content Kris! Learning a lot from you:)
Wow again Kris!
You mentioned in passing about the video or possibly screen shots overread. I think what you did with Elden Ring combined with this style of agents could really open some amazing use cases. Guided education for new software or games of course. But, possibly a broader automation/RPA method for almost any current software available. Examples: Quickbooks to do your taxes, video editing automation, spreadsheet visualizations. Thx!
Thanks for making this approachable. Really appreciate it!
You're making great content, so much fun trying out there projects!
absolutely blown away, great job!
Thank you Kris. Amazing new video as always.
Kris, thank you for sharing the video. I think the verge website is too easy to crawl (verge is also used in the open Interpreter video). Can you try a more difficult website crawl next time? Thank you
sure! thnx :D
Your videos always make my day. Keep shining!
Keep it up Kris! Thank you for all you do. Fingers crossed for this contest!
Great video! Looking forward to implementing agents in my workflow.
Great workflow. Thanks for sharing
These step by step & high level logic overviews are really helpful.
Useful, once again
Great content.
great video! have been looking for this!
Thanks Kris! You mentioned vision model to deal with screenshots. And the results were not so good.
I recommend to try some OCR API. I tested one of them and it worked great even with photos of monitors.
Very interesting. Thank you for this great content!
awesome content. soaking it in! Thanks for the work
I can't believe you made this. future of AI coding Agent! wow!
Great video!
This was going to be my next project but using local LLM's. Anthropic Opus is really good though, so I may have to use it for code writing and self correction.
Nice work!
thnx :)
I’ve been learning alot thanks man!
This is very interesting and should be fun to explore
Fun to watch. How much did this cost you?
I really like the self correct objective - Is this going up on the repo?
Great video, great shirt 😅. Thanks, mate!
I don't see any code links, so I won't watch it.
Let's goo! Amazing content as always! Keep it up Kris
I am curious to know which improvements this code would suggest whilst looking at itself (to have it analyze the code from which it is made)
Perhaps it would build a friendly GUI and such .. who knows really.
Very useful code solving real issues elegantly! - The compliment! 🖖
thnx a lot, i am gonne try that for sure:P
Recent member here. Hello!
hey :)
Keep up the good work!
Thank you for this video!
Thank you Kris, Good job as always!
Interesting approach, gotta try this. Thanks!!
Insane! I am working on a low latency sts and I would love to get some insight on it.
cool :) yeah i think a lot of ppl or working on latecy, i guess if you gonna have a consumer facing product it needs to be low latency, ppl dont have any patience and are used to instant responses
I suppose you are right. As an individual, it is harder to reach a wide audience at the same time but you still pull it off! I think you would be happy to know that I have solved the bugs myself and now adding some spice to the sts assistant :)
One thing I wanted to ask was - how do i get my assistant to stop listening as soon as I stop talking ? RIght now I press 'ctrl+c' to interrupt and stop recording.
Great project and cool to see how it works. What's the initial setup for this?
This is awesome! Thanks Kris!
Great video. Thank you!
Thanks!
You won the NVIDIA merch =) can you send me a e-mail at kris_fagerlie@hotmail.com
Again I have the feeling to dive deeper in coding
I have a similar setup for running SQL
Really cool, thank you!
As always great Video 😁
Thanks for quality content
Super video, will try this out 👌🏽👌🏽
Another great video.
thanks for sharing this , Keep it up!
Thank you for the Video, But how to become member? i see not paid subscription.
It looks interesting - thank you for sharing:)
It wasn't bad at all, good video bro.
I’d love the file download for this, tryna implement somthing for personal use this would be great starting point
thanks for another useful video
This only works with Python code?
I'm a recent channel member. How do I get access to github?
send me a e-mail :)
Try with Groq and see how many tries it gets, maybe quantity is better than quality.
how to become a member?
Thank you!
Super! i am ai. Gracias Kris!
Greetings from Germany.
This is really cool , although , it is pretty much AUTOGEn but basic, isnt it? Do you see any advantage using this scope for self correcting AI instead of using something like autogen or crew ai?
Awesome! No LangChain, no Autogen, no CrewAI, just regular-people code!
Nice content thx
Let's go! I'm a different name on Discord, btw.
I want something like this for my coding assistant
Super fun!
Groq is being a smartass and still adding explanations. Anyone got the proper prompts?
Very nice! :)
You take on projects for commission or hire?
send me a e-mail :)
Pretty darn cool
Been needing another option for running and fixing code. Looking forward to the github release of this one.
Autogen
Should try it with a local model
How is this different FROM AutoGen?
its basicly the same, just a simpler form i guess
In my experience gpt4 is awful when it comes to returning FULL CODE when the code is longer than a few lines. At around 100 lines or before it starts to use placebolders, make up stuff and assume stuff, even things that are clearly defined and described in the code that is provided as context and just plain out hallucinate and break the code.
Claude is the best rn I think
Thanks!
more please
Nice :D can i play with the code isit on your github? you got a link? i have some code for you its 13 + web apps i made using ai i will swap for your github access i dont really like using discord and yt packages can you do a deal?