- 43
- 10 729
JankoWTF
Приєднався 26 жов 2022
Umbauen, anbauen, weiterbauen.
Lebens-Lego bauen, Neugier nachgehen & intutitiv investigieren.
Experimentieren & tüfteln, stolpern & staunen.
Machen.
Und dabei einfach die Kamera drauf halten.
Productivity Stuff, AI Stuff, Coding, Musik, im rollenden WoMo-Studio mit guten Tüpinnen & Tüpen schnacken, Brain Dumps abladen...
Rucksack, Schaufel und Taschenlampe packen und den Kaninchenbau auschecken.
Rausfinden wie dieses Ding called Leben und dieser Dude called Janko eigentlich so funktionieren.
Aber vor allem: Spaß dabei haben! 🤩
✌️🤓✌️
Lebens-Lego bauen, Neugier nachgehen & intutitiv investigieren.
Experimentieren & tüfteln, stolpern & staunen.
Machen.
Und dabei einfach die Kamera drauf halten.
Productivity Stuff, AI Stuff, Coding, Musik, im rollenden WoMo-Studio mit guten Tüpinnen & Tüpen schnacken, Brain Dumps abladen...
Rucksack, Schaufel und Taschenlampe packen und den Kaninchenbau auschecken.
Rausfinden wie dieses Ding called Leben und dieser Dude called Janko eigentlich so funktionieren.
Aber vor allem: Spaß dabei haben! 🤩
✌️🤓✌️
AI Cooking Copilot 🤖🤝👨🍳 Making Cooking Fun Again for Me with ChatGPT Advanced Voice Mode
Brain scattered while cooking? Can't remember the next step? Tired of looking at recipes while storming around in the kitchen? Probably not - but that's my "normal state of being" as my mind always jumps to something "more fun" while I actually should be focussing on the somewhat "boring" task at hand 😅
With trying to start a company and being really short on time, cooking became a nuisance for me - which is a pity as I once enjoyed it. Watch how I'm turning ChatGPT's Advanced Voice Mode into my perfect kitchen companion. No more stress about forgetting what step comes next - just ask "what's next again?", "how much of this?", etc. whenever you need!
This is my first bigger cooking experiment besides having only cooked rice pudding with the AI before 😉 Today we're making Honey Balsamic Chicken, and turns out, having an AI assistant makes cooking actually FUN again for me 😊
What you'll see:
- How to set up your AI cooking buddy with all it needs to know
- Ask anything, anytime (seriously, as often as you need! And I need "often" 😜)
- Why muting your mic brings more "peace of mind" and comfort when using this new tech in your home
- ChatGPT doing the outro 😉
The best part? It's like having a patient friend in your kitchen who never gets tired of repeating things. Perfect for scattered brains like mine!
Give it a try, even if it feels weird at first (trust me, it gets better 😅).
⏱️ Timestamps:
00:00 Introduction and Overview
01:16 Setting Up for Cooking with ChatGPT
03:25 Preparing the Recipe with ChatGPT
06:26 Starting the Cooking Process
08:53 Cooking the Chicken Thighs
11:15 Preparing the Sauce
16:18 Adding Final Touches and Adjustments
23:39 Seasoning and Cooking the Potatoes
32:56 Cooking Mishaps and Realizations
34:46 Adding Forgotten Ingredients
36:02 Cooking Techniques and Tips
38:40 AI-Assisted Cooking Ideas
40:50 Conceptualizing the Chaos Graph
42:45 Engaging the Community
47:30 Final Thoughts and Reflections
01:06:13 Outro and Reflections
In case you try this out 👉 let me know in the comments how it went! Maybe there's peops out there than can relate to my relationship with cooking and how I'm looking for angles to change it again - ai-tech-based, of course 😜 In case there is: let's start a little "Cooking with AI" community!
#ai #AIAssistant #Cooking #ChatGPT #KitchenHacks #VoiceMode
With trying to start a company and being really short on time, cooking became a nuisance for me - which is a pity as I once enjoyed it. Watch how I'm turning ChatGPT's Advanced Voice Mode into my perfect kitchen companion. No more stress about forgetting what step comes next - just ask "what's next again?", "how much of this?", etc. whenever you need!
This is my first bigger cooking experiment besides having only cooked rice pudding with the AI before 😉 Today we're making Honey Balsamic Chicken, and turns out, having an AI assistant makes cooking actually FUN again for me 😊
What you'll see:
- How to set up your AI cooking buddy with all it needs to know
- Ask anything, anytime (seriously, as often as you need! And I need "often" 😜)
- Why muting your mic brings more "peace of mind" and comfort when using this new tech in your home
- ChatGPT doing the outro 😉
The best part? It's like having a patient friend in your kitchen who never gets tired of repeating things. Perfect for scattered brains like mine!
Give it a try, even if it feels weird at first (trust me, it gets better 😅).
⏱️ Timestamps:
00:00 Introduction and Overview
01:16 Setting Up for Cooking with ChatGPT
03:25 Preparing the Recipe with ChatGPT
06:26 Starting the Cooking Process
08:53 Cooking the Chicken Thighs
11:15 Preparing the Sauce
16:18 Adding Final Touches and Adjustments
23:39 Seasoning and Cooking the Potatoes
32:56 Cooking Mishaps and Realizations
34:46 Adding Forgotten Ingredients
36:02 Cooking Techniques and Tips
38:40 AI-Assisted Cooking Ideas
40:50 Conceptualizing the Chaos Graph
42:45 Engaging the Community
47:30 Final Thoughts and Reflections
01:06:13 Outro and Reflections
In case you try this out 👉 let me know in the comments how it went! Maybe there's peops out there than can relate to my relationship with cooking and how I'm looking for angles to change it again - ai-tech-based, of course 😜 In case there is: let's start a little "Cooking with AI" community!
#ai #AIAssistant #Cooking #ChatGPT #KitchenHacks #VoiceMode
Переглядів: 67
Відео
Improve your AI-Assisted Coding: Challenge the First Response! 🤓🤝🤖
Переглядів 2769 годин тому
Stop treating AI like a magic code generator that gets it right on the first shot! Here's how to actually level up your AI-assisted coding game 🚀 Challenge the first proposal of your coding assistant and ask it to double check. Do this as many times as necessary until both the assistant and you are satisfied with the reasoning and assessment. It's basically "manual chain of thought" and it work...
Wiederholst du noch - oder merkst du schon?! 🧠 So nutzt du ChatGPTs Gedächtnis richtig [DE]
Переглядів 13312 годин тому
Was ist noch nerviger als sich alles doppelt und dreifach zu merken? Richtig - es auch noch ChatGPT immer wieder neu erklären zu müssen! 🤪 In diesem Video zeige ich dir, wie du ChatGPTs Memory Feature richtig nutzt. Ist noch lang nicht perfect, ist aber schon sehr praktisch: 1. Proaktiv Erinnerungen setzen lassen 2. ChatGPT gespeicherte Erinnerungen ins Gedächtnis rufen 3. Damit deine Convos au...
Krass sparen mit KI beim Einkaufen? 🤖 Ich bau' den Savings Assistant (und brauch deine Hilfe!)
Переглядів 54День тому
Wusstest du, dass Supermarkt-Angebote einem System folgen? Einem System, das die meisten komplett übersehen! 🤯 Ich zeig dir was Cooles, das ich gerade baue: Saive, dein AI Savings Assistant. Der PoC kann schon: - Automatisch Prospekte scannen - Mit KI Produkte und Preise erkennen Aber das Beste kommt noch: Ich will was entwickeln, das die geheimen Angebots-Zyklen deiner Lieblingsprodukte erkenn...
Save BIG with AI while Shopping? 🤖 Building Smart Shopping Assistant (& I Need Your Help!)
Переглядів 47День тому
Did you know supermarket promotions aren't random at all? They follow super predictable patterns most people never notice! 🤯 Let me show you something cool I'm building: SALVE, an AI shopping assistant. The PoC already: - Scans supermarket flyers automatically - Identifies products and prices with AI But here's the exciting part: I want to build something that learns the secret promotion cycles...
Cooking Up Antifragile Code? 🧑🍳 Advanced Voice Mode for Better Software Design
Переглядів 92День тому
Cooking Up Antifragile Code? 🧑🍳 Advanced Voice Mode for Better Software Design
J.A.R.V.I.S. im Auto?! 🤖 So nutzt du ChatGPT Advanced Voice Mode unterwegs!
Переглядів 62День тому
J.A.R.V.I.S. im Auto?! So nutzt du ChatGPT Advanced Voice Mode unterwegs!
Having Fun with Play.ai: Talking to My Clone That Would Sell Me Long German Words 😅
Переглядів 7314 днів тому
Having Fun with Play.ai: Talking to My Clone That Would Sell Me Long German Words 😅
Having Fun with Play.ai: Turning any Text into a Podcast with PlayNote
Переглядів 6914 днів тому
Having Fun with Play.ai: Turning any Text into a Podcast with PlayNote
Having Fun with Play.ai: Text-To-Speech with French and German (kind of) 😅
Переглядів 7014 днів тому
Having Fun with Play.ai: Text-To-Speech with French and German (kind of) 😅
Mastering Windsurf AI: Top 3 Tips for Better Development & Learning
Переглядів 5 тис.14 днів тому
Mastering Windsurf AI: Top 3 Tips for Better Development & Learning
Schneiden, Schnacken, Schrauben | Trailer
Переглядів 6714 днів тому
Schneiden, Schnacken, Schrauben | Trailer
Schneiden, Schnacken, Schrauben | Folge 1
Переглядів 9314 днів тому
Schneiden, Schnacken, Schrauben | Folge 1
Tinkering Tuesday | Data Analytics to Slides & RHaaS: Rabbit Hole-ing as a Service
Переглядів 15414 днів тому
Tinkering Tuesday | Data Analytics to Slides & RHaaS: Rabbit Hole-ing as a Service
D'oh! Accidental Complexity Strikes Again 🤦🏻♂️
Переглядів 6614 днів тому
D'oh! Accidental Complexity Strikes Again 🤦🏻♂️
I "voice-built" a Xmas Calendar App with AI in 15 Minutes
Переглядів 19221 день тому
I "voice-built" a Xmas Calendar App with AI in 15 Minutes
Einfach ma' machen - im neuen mobilen YouTube Studio (spontane Rastplatz Edition)
Переглядів 1692 роки тому
Einfach ma' machen - im neuen mobilen UA-cam Studio (spontane Rastplatz Edition)
Hab das auch in der kostenlosen Version genutzt Ist echt genial! Hab mir gerade vorhin aber die plus Version geholt, weil ich mit dem geilen Ding einfach viel mehr machen will. :D
Nice! Bock ein paar deiner Use Cases zu teilen?
📖 📕 This is a brilliant idea! A practical guide to prompt engineering for coding with AI is much needed, and a cookbook/playbook format sounds perfect for quick reference. Love the "Hitchhiker's Guide" title! Emphasizing how to prevent breaking existing code, double-checking AI output, and pinpointing potential issues like state management and database interactions when prompting the AI are key. A book that demystifies prompt engineering and puts the coder in control of the AI is exactly what's needed. Focusing on specific coding scenarios and prompt techniques would be super helpful. Count me in! I will print it and put it on my desktop 😊
@@good-dev-student awesome, thanks for the feedback/encouragement 🙂🙏
😂 finally I have bring my coffee and enjoy the show ❤🎉 thank you for your awesome contents tip: try google notebook there are new updates may enrich the videos else you have unique creations keep going
11:56 ich hätte es so gefeiert, wenn er mit "Eijo" geantwortet hätte
Das Risiko war/ist durchaus real 😜 ist ja fast wie Live Coding - und Live Coding geht IMMER schief, wusste schon Pumuckl: "Willst du Live etwas probieren, musst ganz schnell du dies kapieren: was nur kann wird gehen schief, Herr Murphy gibt dir Siegel und den Brief" -- Altes Koboldsgesetz
I learned germany 🇩🇪 😂❤
Dual-use content 😅
😅 yeah... sorry for the mix in languages, I guess 😬 This should soon be sorted out by kick a** AI translations - no matter the camera perspectives and angles, right?! 😉 Until then: appreciate dealing with the dual nature of this channel. It might make sense at some point to do a clear split, but managing two channels is just too much ATM. Appreciate you watching! 🙂✌️
@jankoWTF you my new person inspire me ✨️ I hope be constant on productivity 🙏
@good-dev-student thanks a lot, very much appreciate that 🙂 trying to "show the f**k up" constantly and to stay consistent with my content output - and seeing that my content provides value to someone out there is a great motivation in doing so 🙏
I'm the 272nd subscriber. Yes, for a complex project, around 60% of your collab with AI, you are like a Senior Dev correcting and giving more feedbacks to your Junior Dev, your AI collaborator/assistant. Git version control is important in each step. Yes, good thing there is ` .windsurfrules` that's like a persistent guide to Cascade or other AI assistant. I did that game-plan-like markdown file with a filename like `project_roadmap.md` building each little app components. Like the AI, I also need context awareness stuff, or like tend to review git logs and diffs of what happened the previous day. This is really a good content for Windsurfers or Cascaders or for AI-tool users in general. With AI collab flow, every dev has a junior dev for doing boilerplate codes (or if lucky, a complete app).
Hey man, thanks a lot for the sub - sincerely appreciated 🙏🙂 Good take on the mental model/metaphor "senior dev (you) managing a team of junior devs". For me it feels a bit like the next abstraction level: after the shift from lower-level/imperative to higher-leven/declarative we enter "delegative" territory: you'll need to get comfortable in managing your team of AI agents. Not just pros in this, also cons/pitfalls. Nevertheless the most fitting metaphor for where I see things evolving to
@@jankoWTF Yes, "delegative"--I cannot agree more. I was like an AI Assistant to my previous Senior Dev and Mentor, too. He would just give me prompts (in the form of email or yahoo messenger --no discord or github yet) like "Make me a wrapper in C for SQL queries like (this... and that...), "make me a class of Form (Borland C++) for my UI with these specs... Just read graphics.h header documentation..." My difference with AI aside from 'artificial' brain and very fast reply is that me and my mentor can sip coffee and laugh together. I wish I could do high-five with AI, too. 😅
Ist bei mir eher andersrum im Home-Office, wenn ich freitagsabend den Schalter umlegen kann, um alles auszuschalten und damit offiziell das Wochenende eingeläutet ist 😉
Ja, hängt halt vom Job ab 😉
that's called root composition
Hi there! Thanks, again something learned 🙂
Pretty much how I have started working with AI myself, helped me refine my own approach further, great session. Is the free windsurf any good, can it compete with vs code and a paid Copilot? I'd like to try it yet I am a bit cautious trying new tools, unless I believe them to be a real and relevant improvement over the tools I already master. Otherwise I tend to try to many new and shiny tools and loose a lot of valuable time on what oftentimes is just that, shiny, yet little more.
Thaks a lot, glad it provided value to you 🙂 Re your question: I haven't come back to VSCode plus GH Copilot since Cursor came out as the UX was just sooo much better. So not sure what the current state is and thus I might be a bit too harsh on GH Copilot. In 2023 it made a big performance jump after GH Universe, the same might be true compared to Cursor and Windsurf after GH Universe 2024. Regarding Windsurf: I might be wrong, but I think the free tier won't get you really far if you really want to build something - however it's a fair deal to try it out. I do enjoy it quite a lot as I feel they nailed the "flow UX" aspect in the Cascade frame to the right. Compared to Cursor's "Composer + Agent" (that in itself is a UX fail IMO 😅) it's much less "visually overwhelming" than what Cursor is showing you. It feels sleek, clean, doesn't distract - just feels "right" That being said: due to the Anthropic API rate limits that Codeium seemed to have run into I switched back to Cursor for about a week and have to say: it's also really good/useful. So it's hard to pick a "true" favorite for me right now. I guess I'd put it that way: if I'm looking for more flow and being okay with a bit more "passenger seat" I tend to choose Windsurf while I'd tend to use Cursor if I'm mentally completely engaged in the codebase and thus more in the "driver seat" HTH 🙂✌️
Great idea. I think there was an attempt at this using various Chrome extensions, but it killed the performance in the browser. Regardless, apps like you are suggesting can be useful and specially if you keep a history of prices and compare....
Yes, I think so to. I definitely plan on retaining history - the vision would be to have a "open price DB" that everyone can systematically can contribute to through the app which I in turn see as a web app that is ideally complemented by a smartphone app. I see the app to be completely open source so that anyone can run/deploy it - possibly complemented by a SaaS for those that can't/don't want to run it themselves. Not sure if open source smartphone apps are even possible as I never developed one 👉 we'll figure it out 😉
Great tips/hacks. I like the feature of making it write down the steps in Markdown. I had to resort to copying and pasting.. I have been using Windsurf a bit more recently, I was impressed like you, about how the app worked with you and was able to discuss aspects. The Don't Destroy Code aspect...what I have done is just let it know I want this code in a git repo and before creating anything new we would move to a new branch and let it go wild. However, while I could roll back the code if it buggered things up (which it did), the database changes would persist...which sucks :( For sure knowing a bit of Python and Postgres has helped me to help it. I needed to unravel buggered aspects here and there.. I'm really looking forward to hearing more about your efforts in using Windsurf!
EXCELLENT AND SUPER INFORMATIVE VIDEO - THANK YOU!
Thanks a lot for your kind words 🙂 glad the content helped you
Vielen Dank auch für dieses tolle Video, es hat mir wirklich gut gefallen! 👍 Einkaufs - App ist eine geile Idee ‼ Abonniert‼
Vielen Dank und cool, dass dir die Idee gefällt 😊 Ich würde das Tool einfach super gerne "in der Welt" sehen, über Open Source für Jederfrau frei und kostenlos nutzbar, so wie wir - die Community (in the making 😉) - es haben wollen. Und würde mir nen Ast freuen, wenn Familien damit ein paar Hundert bis Tausend Euro sparen können. Die Idee hatte ich, als ich mal ne kleine Doku über nen Familienberater gesehen hab, der Familien genau in die Richtung erfolgreich berät. Daher bin ich sehr confident, dass das a) musterkennungstechnisch funktioniert und b) geldtechnisch was bringt 🙂
@@jankoWTF Wie weit bist/seid du/ihr schon mit der Umsetzung, ich würde evtl. gerne mitbasteln an der App, falls ich euren Code verstehe !? 45+ Jahre coding.
Ja nice! 🤩 Bin noch komplett am Anfang, hab vor ein paar Wochen mit Bolt nen ersten PoC gebastelt 🙂 Bock auf Discord? Hab iwo noch nen Server rumfliegen 😉 Meld mich gegen Ende der Woche nochmal dazu
Vielen Dank für das tolle Video, es hat mir wirklich gut gefallen! 😊 Ich hätte eine kleine Anregung: Vielleicht wäre es hilfreich, wenn Du im Titel des Videos eine Sprachkennung wie [DE] oder [EN] hinzufügen könntest. UA-cam übersetzt die Titel nämlich automatisch in die eingestellte Browsersprache, was manchmal verwirrend sein kann, wenn die Sprache im Video z. B. Hindi oder Spanisch oder ....ist. Das könnte vielen Zuschauern helfen, sich besser zurechtzufinden. Danke für Deine Mühe und mach weiter so - Deine Inhalte sind klasse! 👍
Moin! Oh, das ist ein super Tipp mit der Spracherkennung! Das wusste ich noch gar nicht, danke dafür und für deine netten Worte 🙂
@@jankoWTF Achte darauf das die Videos nicht ganz gleich in der Länge und/oder Thumbnail sind, meine Videos in anderen Sprachen wurden wegen doppeltem Inhalt gesperrt obwohl Thumbnail und Audio in anderer Sprache waren!
Definitiv geile Idee, ich bin aber nicht in der Lage zu helfen, schätze ich. Vielleicht zu einem späteren Zeitpunkt als Tester 😉
Herzlichen Glückwunsch! Ihre Bewerbung als offizieller Tester von Saive wurde angenommen! Buckle up & stay tuned - spätestens im Januar 2025 geht's weiter 😜
hI jANKOwtf -- rEAD THIS O GIVE IT O YOU AI YO rEAD { "project_management_system": { "main_index": "main.md", "modules": [ { "name": "clients.md", "folder": "clients", "subsections": [ { "name": "clients_gui.md", "tracker": "clients_gui_tracker.json", "details": "clients_gui_details.md", "tasks": [ "Implement React components", "Handle form validation", "Add error handling for API calls" ], "instructions": { "error_handling": "Use try-catch blocks for API calls", "formatting": "Follow the project's coding standards" } }, { "name": "clients_code.md", "tracker": "clients_code_tracker.json", "details": "clients_code_details.md", "tasks": [ "Write backend logic", "Optimize database queries" ], "instructions": { "error_handling": "Use async/await for API calls", "formatting": "Follow DRY principles" } }, { "name": "clients_dependencies.md", "tracker": "clients_dependencies_tracker.json", "details": "clients_dependencies_details.md", "tasks": [ "Install dependencies", "Configure environment" ], "instructions": { "error_handling": "Use npm for dependency management", "formatting": "Check compatibility with project requirements" } } ] }, { "name": "other_module.md", "folder": "other_module", "subsections": [ { "name": "other_module_sub1.md", "tracker": "other_module_sub1_tracker.json", "details": "other_module_sub1_details.md", "tasks": [ "Define module requirements", "Set up testing" ], "instructions": { "error_handling": "Use Jest for testing", "formatting": "Follow TDD principles" } }, { "name": "other_module_sub2.md", "tracker": "other_module_sub2_tracker.json",
Das ist sehr stark
Thanks I enjoyed and learned a lot 😊
Thanks a lot, glad to hear that 🙂
Am Anfang war es sehr ungewohnt für mich, allerdings nutze ich es mittlerweile wirklich mehrmals täglich. Ich danke dir für deine Videos und bin gespannt was noch so kommt 😊😊
Super Video, interessant wie gut es schon funktioniert. Aber ich hab da vergleichbare Probleme, die Sprachausgabe ist teilweise wirklich unangenehm. Und ich persönlich spreche nicht flüssig genug (wegen Denkpausen zwischendurch 😅), weswegen ich dann schon Antworten auf halb gestellte Fragen bekomme und alle Aufforderungen länger zu warten sind bei der nächsten Spracheingabe wieder weg
Da stimm ich dir zu, das ist wirklich noch etwas nervig, mal abwarten was die Entwicklung noch so bringt
Giving it MVP concepts also helps a lot. Also keep on chat mode until you agree with changes. This can save a lot of time for developers that can code. Do not let the AI do what it wants, guide and control every step, and it's quite good. You do need to be a full stack developer to get anything complex from it. Jobs safe for now, phew. Lol
I agree 100 % with your point of "YOU the dev need to be the one calling the shots and closely guiding the AI". I'd just relax/nuance the aspect of "you need to be a full stack dev" a bit: ideally you are a developer that has programmed both backend and frontend cide to some extend - but you don't NEED to be a "complete/true full stack dev" (if this perfectly balanced dev persona even truly exists at all 😉). The message I wanna send here: you NEED to at least be willing to build on top of your existing dev game - no matter your skill/scope level - or be willing to basically learn about each line of code the AI writes for you in case you are just starting out.
@jankoWTF 100% agree. Learning is a never-ending process, regardless of skill set and commercial experience. I'm constantly having to learn. I think windsurf has a place for people with any skill level, like an in-house teacher you can learn from. My 10 year old built an AI to do app with it for his homework, and he learned a heap in the process. It's really amazing.
so helpful. thank you.
Glad it was helpful to you 🙂
I would say Ghost tiny steps by tiny steps every step of the way make sure that you're not moving too many steps at a time Like don't even implement full features but think about whatever feature you want to implement whatever tiny step feature do you want to implement and think about what it requires to be able to implement that and then take that tinier step so instead of a baby step go to like a snail like crawl think about each and every detail of it because if you even go one step and when you're working with AI it can screw up the entire thing which is like a good thing forget you know and make sure your versioning and stuff but not versioning but literally like reiterating over and over but keeping every change. That's my advice from my experimentation.
Thanks for sharing! I've tried a couple of things the last days which seems to work great and might turn it into a little "cookbook" of hacks that seem to work when using Cursor, Windsurf, etc.
I want to see a new IDE made from the ground up with an a particular AI model in mind maybe even with no API access but it the AI model is just included in the IDE and that would mean they would have to be smaller models but could you imagine like a small model or group of models that were trained on individual tasks within an IDE where it's far better because of that division of labor. Like an agentic sort of based IDE that's not related to VS code where the AI can actually track syntax errors and then you could have another one to autocompletion... And I'm talking like really small models You could probably get away with really small models like I think people are underestimating or overestimating the difference of a 1 billion or 3 billion parameter model versus a 300 or 500 or a trillion parameter model I think people are really underestimating the value of these smaller AI models You don't need to own the desert and you don't need to own the diamond fields in order to have effective AI You don't need to be you know among the top 1% of income earners to make valuable and really good AI
Sounds like an interesting idea/take - basically a team of small AI agents working together in a "team space" that could be called IDE but could also be/feel like a evolution of that. Go make it happen! ✊🏻Or maybe a at least PoC of it that you can share. Maybe there are others out there who'll dig it🙂
The fact that like even if you don't know what you're doing you can start and dive into a bunch of stuff and then just try something and then start asking questions and try to modify it and learn why it didn't work but the point really is like you got to make sure that you're asking questions and your your adding to your knowledge base over time.😊
Good video, but please stop calling humans carbon meat bags. It's actually quite offensive.
Appreciate the feedback. I get that calling humans 'carbon meat bags' might not sound great to everyone, and I don't want to genuinely offend you or anyone else. I lean into that phrasing as a tongue-in-cheek way to keep things lighthearted and remind us not to take ourselves too seriously - it's just who I am and how I roll. Different strokes for different folks, right? I hear you, though-let’s just agree to disagree on the style. And thanks again for sharing your perspective!🙂✌
@@jankoWTF Thanks for your reply. The reason I take this seriously is that there is a significant movement to relegate humanity to the trash heap of history, a boostrap, if you will for the next level of evolution to a silicon-based life form. This movement is not just well funded, they are in many cases, the richest and most powerful people on the planet, who have as their goal, living forever, and leaving their "carbon meat bag" history behind them. And they don't plan on bringing you and me or the vast collection of humanity with them. Words do affect people's self conception and thoughts.
Hm, ich bin immer in der Entscheidungsphase welche IDE ich jetzt nehmen soll - Cursor oder Windwurf. Im Moment nutze ich beide und als drittes noch VScode. Langsam wird es aber ein bisschen umständlich ständig zwischen den Dingern zu wechseln ;-)
I feel you - mir geht's genauso 😉 meld mich später nochmal mit ein paar mehr Details dazu
@@jankoWTF Also ich hab mich jetzt endlich entschieden. Es wird Cursor, für den Moment, mit dem ich weiter arbeiten werde. Erstens gibt es, soweit ich das jetzt sehen kann, mehr Modelle zur Auswahl. Zweitens wurde der Preis ja von Windsurf erhöht soweit ich weiß. Drittens hab ich ja noch Claude/ChatGPT/Gemini/Perplexitiy und DeepSeeker die ich quälen kann wenn ich mal wieder unfähig bin und ned weiter weiß.
i was here before you got the 100! keep it up!
Thanks man, appreciate you 🙏
Du machst ja auch klasse arbeit
Merci 😊
Really cool you are good guy 🎉❤ thank you so much
Thanks a lot for the kind words 🙂🫶🏻
One more thing to share, use a git repo and update after each new acceptable step. If you follow the advice in this vid you will have a lot less need to dig into a backup but it is good insurance.
Yes, very good point. I was thinking about synthesizing my observations, learnings and thoughs on how to best combine "non-git-based iteration" with leveraging the versioning functionality offered in the "agentic frames" (= Cascade in Windsurf and Composer + Agents in Cursor) with good ol' git-based versioning. I think aider.chat/ is doing it in the most raw form possible (or at least used to): every LLM code change results in a git commit. IMO, that's a bit too fine granular, but there's definitely a sweet spot 👉 would be awesome if you could share your observations/assessment on where to draw the line! 🙂
great video it totally agrees with my experience with Windsurf and writing SwiftUI code. You are hitting all the points that my experience has shown so this is great guidance for anyone at any coding level
Great to hear that and thanks for sharing 🙂 I feel like we can all help each other out by sharing knowledge and it's awesome to hear that you agree/made similar experiences
du bist cool! mach weiter so. 🔥 ich suchte das video zum dritten mal. just to sponge everything in. 🙌
Moin - und danke für die netten Worte 🙂 Much appreciated 🫶
What a great process plan for starting with AI development. Many thanks.
Many thanks back to you 🙂 glad I can help a bit and that you liked the content 🙂✌️
lol, must be very cold there
Well, it's Germany after all 😉
Kann man den advance voice Mode auch irgendwie einstellen, dass direkt in der Konversation die Antworten auch in schriftlicher Form ausgegeben werden? Also ohne dass ich den voice Chat beeenden muss? Btw. dein Sound am Anfang ist leider extrem "hallig"
I know 🤦🏻da hat iwie mein Mischpult oder Ecamm Live oder beides gehakt - aber: done is better than perfect 😉 Adv. Voice Mode: jebb, alle Convos werden im Hintergrund parallel als "ganz normale textbasierte Unterhaltung" mitgeschrieben
Great video thanks 🙏
Glad you enjoyed it
I don't know but I am getting a resource exhausted error just after one or two prompts in a new chat, and it is relitively slow now to
Yes, it's a problem that all users seem to be facing for the last ~7 days. Seems that Codeium/Windsurf is hitting their API limits with Anthropic and/or that Anthropic itself is struggling to keep up with the demand. The peak times seem to be 3:00 to 9:00 am Pacific Time 👉 if you're able to avoid those, you might be able to get longer Convis running without interruptions. But it is super annoying and "drove me back" to Cursor temporarily yesterday 😉
@@jankoWTF yess, like as of right now it is working like fast but the issue is that it is not fixing the error in my application even when i provide it exact error and solutions for it, it doesn't seem like it is very intelligent as it was a few days ago
What Windsurf is also lacking compared to e.g. Cursor is the ability to link docs and to do web search. The LLM not finding the right approach/solution sometimes simply comes down to the fact that it's operating on "outdated data" in the sense that a certain package/framework has progressed but the LLM doesn't know about it yet 👉 in cursor I usualy hit `@web` or `@docs` and instruct the model to make sure to use the latest developer docs. Another good general strategy usually is: divide and conquer 👉 split the thing you're trying to accomplish up into smaller, well-defined/contained parts and try to tackle each one in a separate convo with the LLM HTH 🙂✌️
I really liked the strategy of persisting the game plan! Thank you for the tip!
Glad it was helpful!
My problem with AI editor is i i dont knlw how to ask AI to make me nice desing or UI in game. And I dont know how to customize.
There are also great tools out there that help with designing. I might do a video on them in the coming weeks. E.g. v0.dev/ is able to take screenshots of a UI you like and then tries to reproduce it
Windsurf also got a similar update recently: ua-cam.com/video/G2bRYbW9VYk/v-deo.htmlsi=TpVNIndQJF-xMzp0
Bolt is better bcs is more fast+smart and you have preview. I mean you can preview your website before download the project also.
For me Bolt and Windsurf/Cursor/etc. are in two different categories: Bolt is awesome to get a very quick prototype that you then would take to Windsurf & friends to improve. However, the immediate preview is something I also came to love in Bolt and miss in Vs studio forks like W8ndsurf and Cursor. But I'm sure that there's a way to get the same basic functionality somehow with a combination of running a live preview server with some Viscose extension. It's on my list of Rabbit Holes to check out sometime 😉
I like only Bolt and WindSurf. Cursor looks shit the desing is terrible. Also i want to ask do you know how i can ask to make me better desing UI on website? Also to to improve Quality? I ask him, but he generates me shit code..
Let me come back to your question on the design aspect. Not a designer myself, but I can try and do some digging for you 👉 ping me Wednesday next week in case I didn't get back to you by then, a'ight?
@jankoWTF no problem but you can make video if you want. Bcs i can forgot tooo
Es ist einfach genau so. Ich lieb es mittlerweile
Nice! Thank you. Any thoughts about making these recommendations part of a context for the agent? Along the lines of .cursorrules files for Cursor? How would this work for Windsurf?
Thanks 🙂 Not having proper settings like `Cursor Settings` with their rules section and/or `.cursorrules` files is one of the crucial features that's still missing for me in Windsurf. I guess as long as that feature set isn't there yet, we're basically stuck to creating such files and telling the LLM to explicitly use it via `@` referencing. I thought about testing, if I can combine this technique with also having markdown files with "prompt templates" in which I would reference the desired markdown files containing rules
Took Perplexity on a spin for exploring a bit and expressing my thoughts based on a FastAPI use case. Convo: www.perplexity.ai/search/the-cursor-ide-has-cursor-sett-sgUBAVHwT6GJRq0X7a.mdg Final gist: Mitigating the Absence of Custom Rules in Windsurf IDE: A FastAPI Developer's Guide As developers familiar with both Cursor and Windsurf IDEs, we've come to appreciate the power of custom rules in guiding AI-assisted coding. While Cursor offers the ability to define .cursorrules files, Windsurf currently lacks this feature. However, this doesn't mean Windsurf users can't achieve similar results. This article explores strategies to mimic custom rules functionality in Windsurf, using a FastAPI project as our example. The Challenge: No Built-in Rules in Windsurf Windsurf, despite its powerful AI capabilities, doesn't provide a direct way to set custom rules or instructions for the AI to follow. This can lead to inconsistencies in code generation and make it challenging to maintain project-specific standards. The Solution: Strategic Use of Context and Prompts By leveraging Windsurf's context awareness and natural language understanding, we can create a system that closely mimics custom rules. Here's how: 1. Create a Rules Document Start by creating a fastapi_rules.md file in your project root: text # FastAPI Project Rules ## Code Style - Use snake_case for function and variable names - Use PascalCase for class names - Maximum line length: 88 characters - Use type hints for all function parameters and return values ## API Design - Use plural nouns for resource endpoints (e.g., /users, /items) - Version all API endpoints (e.g., /api/v1/users) - Use HTTP methods appropriately (GET for retrieval, POST for creation, etc.) ## Documentation - Include docstrings for all functions and classes - Use FastAPI's built-in documentation features (description, response_model, etc.) ## Dependency Injection - Use FastAPI's Depends for all database and external service dependencies ## Data Validation - Use Pydantic models for request and response data validation ## Error Handling - Use custom exception handlers for consistent error responses - Return appropriate HTTP status codes ## Testing - Write unit tests for all API endpoints - Use pytest for testing framework ## Project Structure - Organize code into modules: routes, models, services, dependencies - Keep main.py clean and use it primarily for app initialization and configuration 2. Develop Prompt Templates Create a fastapi_prompt_templates.md file with reusable prompts: text # FastAPI Prompt Templates ## Template 1: Generate an Endpoint Generate a FastAPI endpoint with the following details: - HTTP method: [METHOD] - Endpoint path: [PATH] - Pydantic model: [INPUT_MODEL] - Response model: [OUTPUT_MODEL] - Database interaction: [DB_FUNCTION] - Description: [ENDPOINT_DESCRIPTION] Ensure adherence to our project rules, particularly: - Use of snake_case for function names - Proper type hinting - Comprehensive docstring - Appropriate use of FastAPI's Depends for database interactions ## Template 2: Refactor Existing Code Refactor the following code to adhere to our project rules: [PASTE_CODE_HERE] Focus on: - Consistent naming conventions (snake_case for functions, PascalCase for classes) - Adding or improving type hints - Implementing proper dependency injection - Using Pydantic models for data validation - Improving error handling ## Template 3: Document an Endpoint Create a comprehensive docstring for the following endpoint: [PASTE_ENDPOINT_CODE_HERE] Include: - A brief description of the endpoint's purpose - Parameters explanation - Return value description - Any potential errors or exceptions - An example usage 3. Leveraging Context and Prompts in Windsurf To use these documents effectively: Prime the Context: Open both fastapi_rules.md and fastapi_prompt_templates.md at the start of your coding session. Use Template-Based Prompts: When interacting with Windsurf, reference the templates and rules. For example: text Refer to Template 1 in fastapi_prompt_templates.md. Generate a FastAPI endpoint with the following details: - HTTP method: POST - Endpoint path: /api/v1/users - Pydantic model: UserCreate - Response model: UserResponse - Database interaction: Use `get_db_session` - Description: Create a new user in the system Please implement this endpoint following our project rules in fastapi_rules.md. Iterative Feedback: If Windsurf's output doesn't fully adhere to the rules, provide feedback: text The generated code doesn't fully adhere to our project rules. Please adjust: 1. Use snake_case for the function name as specified in our code style rules 2. Include a more comprehensive docstring as per our documentation rules 3. Implement error handling using custom exception handlers as outlined in our error handling rules Regular Rule Review: Periodically review and update your rules and templates: text Please review fastapi_rules.md and fastapi_prompt_templates.md. Suggest any improvements or additions based on current FastAPI best practices and our project's evolving needs. Conclusion While Windsurf doesn't offer built-in custom rules like Cursor, this strategic use of markdown documents and prompt templates can effectively guide the AI to consistently follow project-specific standards. By integrating these practices into your workflow, you can maintain code quality and consistency in your FastAPI projects, leveraging Windsurf's powerful AI capabilities while mitigating the absence of explicit rule-setting features. This approach not only helps in maintaining coding standards but also serves as living documentation for your project, ensuring that all team members are aligned on best practices and conventions. HTH 🙂✌️
@@jankoWTF I've played around a bit with that and while it works, it does so inconsistently. It's still a bit hacky, it'd be great to see it as a feature in the future!
Yes, definitely - IMO it's the biggest thing that's missing, followed by being able to systematically reference docs like with @docs in Cursor and/or being able to do a web search to nudge the LLM to the most recent developer docs
However, regarding consistency I also felt like Cursor only follows the rules in about 70-80% of occasions.
Thanks! I would really love to see a video where you can create front end with AI coder and then connect it to authentication and database like a real saas
Thanks 🙂 So your main point is how to take a "frontend only" that might have been generated by, say Bolt, V0, Replit Agent or something similar and then go and "fix" backend infra that the tools might have missed? Or are you rather referring to creating a full stack app through/with Cursor, Windsurf, IDX or similar "true IDEs"? I'm actually planning on creating a little "idea backlog app" with stackoverflow-like upvote/downvote features to co-create video ideas together with my viewers/the community. Maybe we can make this a win/win: I try and showcase something along the lines what you're imagining and it's for this particular idea backlog app that will help others in expressing similar ideas in the future 🙂
It's crazy how close your clone is after only 30 Seconds Input
Totally! Impressive
But ElevenLabs has also been cooking again: ua-cam.com/video/v-EYzZCLF48/v-deo.htmlsi=AVvqhaB_xiR1CIXC ua-cam.com/video/iL0zMDUKt6w/v-deo.htmlsi=LyXF4rS7-ek11nQ6
5:20 Himmel Arsch und Zwirn totally killed me 😂😂
Me too 😅
Hat echt Spaß gemacht! ❤❤❤
Zum Glück seid ihr dann doch beim Hochdeutsch geblieben. Ich liebe saarländisch, aber es im TV oder Videos zu sehen/hören ist total cringy 😂
😅
Geiler scheiß
Hey Janko, thank you very much for answering my question in this detailled way! I will at least play a little bit with Gamma, I see that there is a lot potential for technical support, but of course from content perspektive it is not yet able to summarize a complicated topic in a few meaningful slides, right? In regards to Claude I feel like it is more a tool to create an specialised app that then would be able to perform Data Analytics and create a presentation in e.g. Powerpoint, right? It seems too complex to just perform a Specialized Task. But as you mentioned for me it looks like a great tool to improve the 'translation' of user requierements into draft/mocks that are easy to understand by development. Especially in regards to common Setup of global IT Departments where different languages and cultures increase the complexity of bringing end-users and development together! Great Video!❤
Thanks 😊 Yep, summarization of more complex data scenarios and adhering to formal guidelines like a PowerPoint Master/Template are still a bit of a stretch or at least I don't know any tools yet that do exactly that. But I'm 100 % that these and similar demands will drive respective product development. The best way as of today would probably/arguably be to take one of the AI-infused automation/orchestration tools such as zapier.com/, www.make.com/en, n8n.io/ or vectorshift.ai/ (& similar no-code AI agent tools) and create a pipeline that meets your specific needs. Might be a good topic for a future RHaaS video 😉 Regarding your question about Claude: Claude is great to prototype ideas quickly, but as you correctly identified not suited for actually carrying production workloads.