- 44
- 71 089
Eduards Ruzga
Latvia
Приєднався 16 чер 2008
Welcome to my channel!
I'm a seasoned Software Engineer with over two decades of coding experience.
Throughout my journey, I've come to believe that it's not about coding as a process, but the results that can be achieved with this powerful tool.
Inspired by Carl Sagan's quote, "We make our world significant by the courage of our questions and by the depth of our answers," I strive to ask thought-provoking questions and seek in-depth answers. This passion drives me to learn by doing, build, create, and share what I built and learned with others.
Join me on this exciting adventure as I explore the realms of generative art, games, startups, programming, and visual storytelling.
If you enjoy my content and would like to support my work, consider buying me a coffee at www.buymeacoffee.com/wonderwhyer.
Don't forget to subscribe and be a part of this ever-growing community of curious minds and innovative thinkers!
I'm a seasoned Software Engineer with over two decades of coding experience.
Throughout my journey, I've come to believe that it's not about coding as a process, but the results that can be achieved with this powerful tool.
Inspired by Carl Sagan's quote, "We make our world significant by the courage of our questions and by the depth of our answers," I strive to ask thought-provoking questions and seek in-depth answers. This passion drives me to learn by doing, build, create, and share what I built and learned with others.
Join me on this exciting adventure as I explore the realms of generative art, games, startups, programming, and visual storytelling.
If you enjoy my content and would like to support my work, consider buying me a coffee at www.buymeacoffee.com/wonderwhyer.
Don't forget to subscribe and be a part of this ever-growing community of curious minds and innovative thinkers!
Fully Free Bolt.New! - bolt.myaibuilt.app - Online, Zero Setup Zero Cost AI-Powered Full-Stack Apps
#BoltNew #AI #OpenSource #WebDevelopment #FullStack #Coding #StackBlitz #AItools #FreeIDE #LiveCoding #WordPressOfAI
Bolt.New is here! A new, powerful tool for building full-stack web apps with AI-better than the competition, open source, and completely free. In this video, I compare Bolt.New to products like GetLazy, Repl.it Agent, and GPT-Engineer, and show you how I made it fully free to use with OpenRouter AI support and project downloads. No setups, no costs, just pure AI-powered development!
🔗 Try Here For Free: bolt.myaibuilt.app
🔗 GitHub Repo: github.com/wonderwhy-er/bolt.new-with-download-project-as-zip
Chapters:
00:00 - Intro
00:17 - Bolt.New from StackBlitz
00:28 - Few other options?
01:28 - It's fully open-source and extendable!
02:03 - I was so excited that I made a fully free version of it!
02:58 - You can add your own key to use premium models!
04:08 - But it works fine with Gemini 1.5 Flash which is FREE!
06:25 - Project download, Other feature I added to open source veri
07:22 - Growing community around Bolt.New
09:18.- What are we doing next time? You Decide!
Bolt.New is here! A new, powerful tool for building full-stack web apps with AI-better than the competition, open source, and completely free. In this video, I compare Bolt.New to products like GetLazy, Repl.it Agent, and GPT-Engineer, and show you how I made it fully free to use with OpenRouter AI support and project downloads. No setups, no costs, just pure AI-powered development!
🔗 Try Here For Free: bolt.myaibuilt.app
🔗 GitHub Repo: github.com/wonderwhy-er/bolt.new-with-download-project-as-zip
Chapters:
00:00 - Intro
00:17 - Bolt.New from StackBlitz
00:28 - Few other options?
01:28 - It's fully open-source and extendable!
02:03 - I was so excited that I made a fully free version of it!
02:58 - You can add your own key to use premium models!
04:08 - But it works fine with Gemini 1.5 Flash which is FREE!
06:25 - Project download, Other feature I added to open source veri
07:22 - Growing community around Bolt.New
09:18.- What are we doing next time? You Decide!
Переглядів: 7 598
Відео
New ChatGPT Canvas vs. Claude Artifacts: HTML/CSS to WebGL Refactoring
Переглядів 13 тис.14 днів тому
#AI #ChatGPT #ChatGPTCanva #ClaudeArtifacts #CodeEditing #WebGL #AIComparison #AIRevolution #webdevelopment #programming In this video, I put ChatGPT's new Canvas feature head-to-head against Claude Artifacts in an AI-powered code editing showdown! Watch as I test both tools by converting a CSS/HTML 3D cube into WebGL. Can ChatGPT's pinpoint edits outperform Claude’s live preview? Let’s find ou...
Build Prototypes for AI's Industrial Revolution with this WebSim Prompt
Переглядів 1,9 тис.21 день тому
#WebSim #AIApps #RPGCreation #aicoding #KnowledgeWork #AIRevolution #industrialrevolution #prototyping In this video, I introduce a new concept for the future of knowledge work: assembly lines of knowledge work. Watch as I use WebSim’s example prompt to create a fun and unique RPG character brainstorming app that takes simple user inputs and converts them into AI images and stories. I also shar...
In Fact-Checking Sources mean more then Reasoning: OpenAI o1 vs GPT-4o vs Perplexity Battle!
Переглядів 587Місяць тому
In this video, we pit several AI models against each other in a fact-checking challenge. OpenAI's new o1 model writes a detailed research plan, which is then executed by GPT-4o. We also test custom GPTs and Perplexity, a startup focused on internet research with AI. Can the combination of o1’s uncensored internal reasoning and GPT-4o's execution outshine the competition? Watch the video to find...
OpenAI o1 VS Sonnet 3.5 in Coding Physics Games - AI Showdown
Переглядів 21 тис.Місяць тому
In this video, we put two AI models to the test: OpenAI's new o1 and Sonet 3.5 from Antropic using Claude and WebSync. We challenge them to create a car parking simulator with realistic physics. Watch as we explore the capabilities of o1's advanced reasoning and see how it stacks up against Sonnet 3.5 Links: Failed Claude artifact: claude.site/artifacts/3949a0f2-3597-4ad7-99c9-3220a9415a42 Fail...
Run code locally from ChatGPT! Run, Test & Debug Too! (Beyond WebSim Part 2)
Переглядів 1 тис.Місяць тому
Are you using ChatGPT to help you write code? Do you find yourself constantly copying and pasting between ChatGPT and your local environment? In this video, I’ll show you how to make ChatGPT even more powerful by allowing it to read, edit, run, debug, and test code directly on your machine. Introducing ChatGPT Server Commander-a tool I created that you can install on your local machine to turn ...
Pushing beyond WebSim Limits: What Happens When WebSim Apps Get Too Big? (Part 1)
Переглядів 846Місяць тому
#WebSim #AIAutomation #AItools #ClaudeAI #Aider #GithubCopilot #ServerCommander #LowCode #NoCode #AIAppDevelopment #AGI #artificialintelligence Have you ever wondered what happens when an AI-generated app gets too big for its own good? In this video, I take WebSim-a powerful AI tool that uses Anthropic's Sonnet 3.5-and push it to its limits. Watch as I explore what goes wrong when apps get too ...
RunwayML for Video effects is crazy 0_o
Переглядів 138Місяць тому
RunwayML for Video effects is crazy 0_o
Even better than Claude Artifacts? And for free? What can't you make with this?
Переглядів 15 тис.3 місяці тому
Even better than Claude Artifacts? And for free? What can't you make with this?
Claude 3.5 Sonnet Artefacts vs ChatGPT: Deep dive - Which subscription will I cancel in a month?
Переглядів 1,7 тис.3 місяці тому
Claude 3.5 Sonnet Artefacts vs ChatGPT: Deep dive - Which subscription will I cancel in a month?
Video Chop Chop - Dev Log - Local in Browser Video Transcription and Editing with Whisper and FFmpeg
Переглядів 634 місяці тому
Video Chop Chop - Dev Log - Local in Browser Video Transcription and Editing with Whisper and FFmpeg
Are you Custom GPT creator? Want to export your GPTs list as CSV or HTML Gallery?
Переглядів 1864 місяці тому
Are you Custom GPT creator? Want to export your GPTs list as CSV or HTML Gallery?
AI for Everyone: 4 Simple Use Cases for Fun and Profit - Presentation from TechChill 2024
Переглядів 3255 місяців тому
AI for Everyone: 4 Simple Use Cases for Fun and Profit - Presentation from TechChill 2024
Will AI End Traditional Coding? Chronicles of making ChatGPT write code
Переглядів 2586 місяців тому
Will AI End Traditional Coding? Chronicles of making ChatGPT write code
My Presentation Secrets: Prezi AI, ChatGPT, Leonardo.ai, & Magnific.ai and Without Speaker Notes!
Переглядів 3736 місяців тому
My Presentation Secrets: Prezi AI, ChatGPT, Leonardo.ai, & Magnific.ai and Without Speaker Notes!
Suno.ai Industrial Rock about looking for Christmas gifts #aichristmas #aisongs
Переглядів 4810 місяців тому
Suno.ai Industrial Rock about looking for Christmas gifts #aichristmas #aisongs
Can ChatGPT be used to read books from knowledge files? Exploration for CustomGPT creators
Переглядів 18410 місяців тому
Can ChatGPT be used to read books from knowledge files? Exploration for CustomGPT creators
So you want to protect your Custom GPTs?
Переглядів 89210 місяців тому
So you want to protect your Custom GPTs?
Urgent news about Custom GPTs vulnerability. Code Interpreter is shared between chats
Переглядів 6 тис.11 місяців тому
Urgent news about Custom GPTs vulnerability. Code Interpreter is shared between chats
Is This Me?! Creating Unique Resumes with Dall-E 3 and Deepfake Tech
Переглядів 23011 місяців тому
Is This Me?! Creating Unique Resumes with Dall-E 3 and Deepfake Tech
Growing trees in ChatGPT with JavaScript Interpreter
Переглядів 57Рік тому
Growing trees in ChatGPT with JavaScript Interpreter
Making Audio Visualiser with ChatGPT JavaScript Interpreter
Переглядів 26Рік тому
Making Audio Visualiser with ChatGPT JavaScript Interpreter
Adding Image Text Recognition to ChatGPT using ChatGPT JavaScript Interpreter
Переглядів 40Рік тому
Adding Image Text Recognition to ChatGPT using ChatGPT JavaScript Interpreter
Making D3 Bar Charts with ChatGPT and JavaScript Interpret
Переглядів 67Рік тому
Making D3 Bar Charts with ChatGPT and JavaScript Interpret
Adding a lot of text to ChatGPT using ChunkGPT Bookmarklet
Переглядів 34Рік тому
Adding a lot of text to ChatGPT using ChunkGPT Bookmarklet
To Bee Or Not To Bee Programmer Timelapse
Переглядів 759 років тому
To Bee Or Not To Bee Programmer Timelapse
Garage48 LudumDare 31 Designer TimeLapse
Переглядів 649 років тому
Garage48 LudumDare 31 Designer TimeLapse
Coleman made a fork that can use other models
I know it's a bit unclear in what state it is, PRs are not being merged so far. Should be community-driven somehow. Am pondering merging with his efforts and others there. I am planing a small video for tomorrow and will mention his there too. There is also Bolt.New office hours tomorrow, plan to ask there for their view and "plans" for the open source part of Bolt.
it is great but the only issue after the first prompt it doesn't allow a second and an error pops up
Open saas is also open source if u can compare two that will be helpful
Excellent video, this is amazing. Thank you for sharing that... I downloaded the git repo but now I don't know the steps to open it in my browser. Can you help me? I subscribed to your channel.
If you run npm run build and then npm run start it will show you hints PRess b for browser and it will open in browser
Cole Medin (a youtuber) is doing the same thing, contact him and colaborate
I did, contact, connected, looked into his repo, and considering to merge efforts There is also StackBlitz office hours tomorrow that I plan to visit and ask them about their views on open source part of Bolt
Try Here For Free:Bad gateway
looks fantastic. I get "bad Gateway" when I click on the app. I'm using linux
You should reach out to coleman, he was that first contributor in the list that you showed. He is so excited just like you are to do what you refer to as a community edition / version. Would be nice if you and all of us could work together.
Would've liked to try it before diving into the GH repo! Are you aware it's offline currently? And great job!
Sadly code is written to run on CloudFlare workers... And I am trying to run it on my digital ocean instance. Which proceed to be hard and I spent too much time on it so far. Can't decide between refactoring it to run on Node or figuring out how to run it with github.com/cloudflare/workerd I restarted the server and will make a video of how to run it locally tomorrow.
While I am figuring out how to deploy it on my own server in stable way I deployed to cloudflare You can try there as alternative 9356f8c3.bolt-2xk.pages.dev/
And thanks! I subscribed, looking forward to seeing how you get on
Thanks for the sub!
Would love to know how to run it locally. I could probably work it out, but it would take me a week at least :(
Will try to make a short video tomorrow
Realy nice fr
Thanks 💯
Yes. Pool resources. Yes. I want contribute to yours or Cole Medin But..for theife of me I could not get this rmrhing running on my windows box or docker container. ...frigging cloudflare wrangler Yes, a video of how to get it running locally...i can tthen lush a PR to add docker container stuff
Yeah... I am suffering from that wrangler/cloudflare thing too... Spent most of my time around that so far and will need to spend more. I am running it in dev mode currently and it crashes 2-3 times a day. There is a way to run it in development mode locally And there is a way that was not added to run it in production mode too using github.com/cloudflare/workerd I can't yet decide if I want to refactor it to node.js or to try and use workerd Both have their pros and cons...
About running locally, will try to make a short video tomorrow
Is that supporting python frameworks as backend? Like fastapi?
No, Bolt uses Web Containers that can do backend javascript. In theory python can be added too, there are web interpreters for it. There is another product called e2b.dev/ They have python in similar setup, but there it runs in containers on server side which is way more challenging thing to self host. Still, if you are interested in python on server side + open source, then take a look in that direction. It just works slower as its server side containers. And more expensive to run.
Not fully. 250k-300 chars daily, 10mln month, 70% errors - still not worthy to pay.
There is rate limit, it is still free though. I just rechecked and Open Router for free models gives 20 requests per minute and 200 per day, but this is per API key, you can add your own API key to get more and still use free models About 70%, you reference some kind of comparison for Gemini 1.5 Flash?
Great work you've sone here @EduardsRuzga ,but i get this error. "There was an error processing your request" Tried Gemini Flash 1.5 and Llama3.1 and others and they all give the same error. Running the Chrome Canary Browser and the standard chrome browser
This is my first AI video where I am taken on a tour in the mysterious world of AI by an experienced guide who has strong technical skills, communication skills, despite English nor English culture are his background. It is very satisfying to see that this person is authonic and not another perveyour of AI hype . We are in difficult times and only people like him: pragmatic, humble, curious, realistic will help us navigate to a succesul future. I have watched many AI vodeos in the past 12 months, and this is he first time I felt the urge to compliment these sentiments.
@@louisfeges2913 thanks for kind words Luis. Trying to strive for what you describe.
Thank you for this. Yes I want to learn how to use it locally
Do you want to use it with local models too? There are some forks that already support that May be I will do a short video later on that
"there was an error processing your request" when i put anything on that box. So if i say create a landing page... and press enter, i get that message. It won't work.
which mode is selected for you? gemini?
@@EduardsRuzga yes. Gemini 1.5
@@nocapnobs7845 yeah, getting it too, will be investigating this week
While I am figuring out how to deploy it on my own server in stable way I deployed to cloudflare You can try there as alternative 9356f8c3.bolt-2xk.pages.dev/
I tried bolt.new-any-llm with Ollama and Gemini Pro. it doesn’t give me desired output..
Man ! you deserve a Noble Prize for this.....
Lol, that's too much praise :D So many before me in StackBlitz, OpenRouter, Google and on and on Thanks! Still things to do for this to be more useful.
Getting bad gateway error for your link
I am really interested in the content you create and are planning to create. Good job and keep up the good work!
It is really good; I also like the way bolt.new-any-llm method of implementation
What do you like about bolt.new-any-llm? I would love for the community to sync on 1-2 forks, currently, there are a dozen forks where some work is being done. Am exploring whether it makes sense to merge with bolt.new-any-llm Not sure yet as there are two "directions" with this that are bit hard to synchronize currently. One is using it with local things like docker, ollama, lm studio. Which is not a good thing for total nondevelopers. Another one I am interested in is a hosted solution on websites that require setup to run. And I am not yet sure how to allow a single project to serve both directions.
link doesnt work
seems I have some issues, second crash of the day, give me a sec
Restarted, will try to investigate bit later of why it crashes
@@EduardsRuzga Fix it please broooo
Great work, Eduards ! Can you please also show how to use locally step by step? Getting always the same error message while trying to run it locally from Cursor! *** Received structured exception #0xc0000005: access violation; stack: 7ffb81be2f57 7ff7d30fc92b 7ff7d30fc9f3 7ff7d30eb18c 7ff7d30eb137 7ff7d293709e 7ff7d29373af 7ff7d1761ee6 7ff7d2ab188f 7ff7d2ab8b26 7ff7d2ab1d93 7ff7d2ab8b26 7ff7d2aaf72c 7ff7d1751e61 7ff7d420382f 7ffb90bf53df 7ffb91a6485a
Great job. Is there a possibility to work with attachments?
What do you mean by attachments? Images?
@@EduardsRuzga yes, images. In Bolt chat i do not see the option to upload an image.
@@HonorHasCome it is possible to add, not on top of my list yet, with multiple model selection part of the problem is that not all models support it But noted, will see bit later
@@EduardsRuzga tnx
Thank you so much for this video❤
Great work done. Thank you. Please consider adding LLM like Ollama.
You mean local llms running on your machine? My focus is on hosted solutions that do not require local setup. I wonder if one can use a hosted solution that connects to localhost as a provider. I use LM Studio myself never found local models good enough
When deploying on ec2 instance and using it we are getting core issue due to which sometimes container , code and preview don’t work . When we use small models also we get the same error. If you have a solution for the same it will be nice to have. Also have you tried integrating with AWS bedrock Anthropic models.
Preview seems not to work due to problems with running terminal commands, it's on my list of things to fix next As for AWS bedrock models, no, I saw some others forks adding that, check forks if you need it in timely manner I hope we can organize in to community that adds such things together, plug and play style. Need AWS models, just flip a switch
Hi @EduardsRuzga Can you add RAG function ?
RAG of what type? RAG is basically indexed text snippets to be added to context when needed, what should be indexed and pulled out?
Is there a limit to the number of prompts we can do? I keep keeping this error after the first prompts “there was an error processing your request”. What is the solution to this?
There should not be, but I just had a crash of my server, will need later to investigated what happened
@@EduardsRuzga thank you very much, please do update us when the investigation is complete
While I am figuring out how to deploy it on my own server in stable way I deployed to cloudflare You can try there as alternative 9356f8c3.bolt-2xk.pages.dev/
Appreciate you man
Thanks!
🎉🎉🎉🎉🎉
Спасибо!
Спасибо!
Not heroes where capes. Thanks.👍
🔗 Try Here For Free: bolt.myaibuilt.app 🔗 If the above is down you can try this too: 9356f8c3.bolt-2xk.pages.dev/ 🔗 GitHub Repo: github.com/wonderwhy-er/bolt.new-with-download-project-as-zip Chapters: 00:00 - Intro 00:17 - Bolt.New from StackBlitz 00:28 - Few other options? 01:28 - It's fully open-source and extendable! 02:03 - I was so excited that I made a fully free version of it! 02:58 - You can add your own key to use premium models! 04:08 - But it works fine with Gemini 1.5 Flash which is FREE! 06:25 - Project download, Other feature I added to open source veri 07:22 - Growing community around Bolt.New 09:18.- What are we doing next time? You Decide!
the link to yours isnt working would love to work on this with you further keep up the great work
@@ChrisMateo-q6s there is other popular repo, i am thinking weather its worth merging efforts or not considering there are interests of running it it locally and in self hosted variant.
While I am figuring out how to deploy it on my own server in stable way I deployed to cloudflare You can try there as alternative 9356f8c3.bolt-2xk.pages.dev/
Hey couple of questions :) can we still use our anthropic key with your fork ? And do you think upload is doable :o?
No, in my fork its open router now. Upload can work but i need to try. It msy glitch in unexpected ways. I think I can add antropic back as option. Probabky need to make popup setting fir choosing provider and model, too much for header.
@@EduardsRuzga thanks!!!!
too bad the sound not so clear :(
@@Ony_mods hey, yeah technical mistake on my side. I will do recap video later that will be shorter and rerecord audio better. Will leave comment here when its published.
I published video a day ago ua-cam.com/video/wAjewqnzq7M/v-deo.html
There are still tons of bugs and support is extremely unhelpful . They essentially offered a refund and told me to use a different platform. The issues were never resolved. it's a great idea but I would five it a few months before paying again. Also, you burn through the 10 million tokens in a few hours of real coding. You would need at least 50 million tokens a week. Mostly due to the system creating errors then taking hours to fix the errors. Not worth it yet.
Did you use any others? Replit and GetLazy feel even worse for me. What I am excited about here is that it has open source, self host variant. I already extended it to use free models, no need to pay. Need to host it now. Soon ;)
on the east coast missed the live stream but will watch replay
Yeah, sadly being in eastern EU and having kids home in the second half of the day puts me not in the best spot for live streams for the Western hemisphere.
@@EduardsRuzga family first, keep up the good work
@@jpoole4931 agreed and thanks!
Stream is over: What was achieved was pushed to this repo: github.com/wonderwhy-er/bolt.new Mainly two things were done: - add support for open router and custom API keys set from client - the ability to export project as ZIP There was an issue with the sound, my setup was capturing and streaming the microphone, but also capturing device audio with lag, so there was an echo.
it is not webgl u clown… and the worst part is u dont even know
most missing feature is running the code in the browser
I agree, am actually working towards having a platform that allows ChatGPT to run code in the browser. But there is more than that and it's not the main part of it.
doesn't seem like a difference big enough to buy gpt premium, i'm doing fine with small unlimited models and in ide copilots and claude sonnet free daily queries for now. The stuff i'm doing is simple, maybe i'll change my mind when i need something more compex. Breaking down problems and asking for each step makes it easier for them to do it and lets you have control on what you are doing. I'd like to hear if others with more experience think i'm wrong.
@@WaveOfDestiny yeah, could be. I am heavy user, use it for writing, brainstorming, summarising, making image ideas. But there are so many free tools out there that if you are occasional user you can do with using free tiers of a dozen of offerings.
It doesn’t use the newest 4o 1 models, so it’s a pass for now
Chat is very very bad. It has you running around in circles with useless code
This was first impressions video and here it did quite well. I am testing it more and there are issues. It does fail with complex files. I also tried one workflow that did not work for me anywhere else. Give it a UA-cam transcript in a canvas, ask to think of good places to split it to chapters in chat, then add them in appropriate places of transcript as comments. If you ask to do the mall at once it fails, but one by one it succeeds and Claude or Gemini can't do it well... And one can imagine similar tasks for code. You can ask it to make comments, and then selectively apply them. That is different from Claude that does everything in one shot and also fails spectacularly depending on complexity of the task. I really hate how Claude always rewrites and as task becomes more complex it rewrites with more and more mistakes... Will see over next weeks as I find more of productive workflows with it Anyways, that is my experience, yours is different, care to share more? What tools do you use?
bolt.new does
@@tomascoox yeah, tried it once so far. I would compare it to gptengineer, replit agent, getlazy though. It is solely focused on coding and has deploy options. First impression of bolt was good, better then alternatives. What is yours?
what extension are you using to speak to your computer, looks cool. seems you have a cool extension list. May be make a video on extensions that you use for developers
I use Voice In It's not superb, multiple other solutions are not good too chromewebstore.google.com/detail/voice-in-speech-to-text-d/pjnefijmagpdjfhhkpljicbbpicelgko The best one is in ChatGPT mobile and desktop apps. But that can not be used out of them. I am thinking of making my own extension that uses webgpu accelerated whisper Based on this huggingface.co/spaces/Xenova/realtime-whisper-webgpu
Ai beliv jou better lern inglish
Not only AI, my wife thinks so too :D And she is not AI :D But in all seriousness, yes, that is one area to improve.