This AI Coder Is On Another Level (Pythagora Tutorial)

Let's build an LLM Benchmarking application with 1600 lines of code without writing any code ourselves.
Get early access to Pythagora: pythagora.ai/v...
Download the OpenSource code: github.com/Pyt...
Here's the app I built: 31711443-d24d-...
Prompt Used in the App: docs.google.co...
Total cost to build = $33
Join My Newsletter for Regular AI Updates 👇🏼
www.matthewber...
My Links 🔗
👉🏻 Main Channel: / @matthew_berman
👉🏻 Clips Channel: / @matthewbermanclips
👉🏻 Twitter: / matthewberman
👉🏻 Discord: / discord
👉🏻 Patreon: / matthewberman
👉🏻 Instagram: / matthewberman_ai
👉🏻 Threads: www.threads.ne...
👉🏻 LinkedIn: / forward-future-ai
Media/Sponsorship Inquiries ✅
bit.ly/44TC45V

[@matthew_berman]

What features should I add to my LLM benchmarking app now?

[@satyajitbeura_factscheck]

How about adding a feature where the app automatically predicts how many times I'll miss a semicolon in my code? 😅 But seriously, maybe an AI-based optimization tool that suggests performance tweaks based on the benchmarking results would be awesome! That way, it could help developers fine-tune their models even further. 🚀

[@Tech_Enthusiast_001]

I honestly love this. As a developer myself... kinda looking to "ascend" and move on to another field, before I am useless,... this kinda content is just great. Would love to see more of these tools, or maybe a video guide on how the hell you find all this stuff and AI news. It just seems so overwhelmingly plentiful and I miss great stuff more than I am happy with.

[@ScottzPlaylists]

🤔 Let users submit QA pairs , and AI categorizes them by similarity to existing benchmarks, and adds to your public DB. 🤔 Users could also specify URL source or Dataset name, or select "Human created" / "AI created from prompt ____ " 🤔 They could be ranked by uniqueness (aka "perplexity"). 🤔 Users could benchmark against their choice of LLM manually and share or post the Q and A manually or the Chat link.

[@magm009]

Add a feature to "clone" an existing test. I'd imagine in the future you'd want to keep historical records, but test new models, this way it can be quick and easy to copy the test statement, expected results, etc, and make it easier to select other models.

[@rajofearth]

just use better passwords: admin benchmark-pw and it's good that you revoked you api keys: s%3AFDJ0Nm3ldhK-5OOQvjpyqIiMY6WuPCEU.xt2iM0IIhFplK4slv5x4McAAnqY4cejQS7K9QL2r6uI

[@ginebro1930]

I like how AI started taking the "fun" jobs first and left us with the worst ones.

[@HawkX189]

I'm a dev and this is exactly what I don't want to do. Spending my time doing what I've done hundreds of times. So please AI more of this "fun" please.

[@kristianlavigne8270]

Writing low level code is not “fun”, at least not for seasoned developers. The fun part is coming up with ideas and getting them implemented and launched… 😊 just like an architect vs construction workers

[@sungm2n]

@@kristianlavigne8270I agree. It’s now becoming more like AI builds Lego blocks and we get to put them together to build something based on our ideas.

[@KeeperOfSolitude]

@@kristianlavigne8270 agree, the programmer carreer is finally disposable, just engineers allowed

[@tiagotiagot]

Don't worry, the robots are coming...

[@sustainitech]

Matt, this is the most useful video of the year, hands down. And you’ve published some great ones so this is a real accomplishment. Thank you.

[@matthew_berman]

Thank you so much!

[@DoppsPkin]

bro, it was an ad

[@Phagocytosis]

@@DoppsPkin Could still be useful!

[@lekobo]

@@DoppsPkinEven so, way much better value than 99% of the AI cliches on KZbin.

[@JustinLietz]

This is incredible, I feel like what we now consider “boilerplate” code is going to be far more fleshed out thanks to tech like this

[@egrinant2]

Dev here, this is fantasy/science-fiction, no client ever will make a such detailed briefing without changes. Jokes aside, I've tried Pythagora in the past and it's amazing, just some caveats: - It's not for simple applications, it will create user roles / auth endpoints even if you tell it not to, or you don't need to. - I've tried with GPT 3.5 Turbo and as I said it was amazing, but if you try to use it with models locally it will fail to provide the output as Pythagora expects it.

[@stevenmedina4030]

thanks a lot for that insight!

[@desmond-hawkins]

If you've only tried 3.5 Turbo, you should try 4o and o1-preview, they are far ahead.

[@jeremylane7652]

local like llama? new models seem very nice.

[@khalilkasmi5760]

really like the videos Matthew, keep it up

[@pruff3]

In theory I like Pythagora, seems like the right angle

[@RickTonoli]

I see what you did there...

[@jaywulf]

Dont be obtuse

[@tmangono]

Yes especially to solve an acute problem.

[@mccall7122]

@@jaywulf He's not obtuse. He's right.

[@richardbeare11]

I think that sums it up squarely 👍

[@golden--hand]

How far off do we think we are from having this kind of development with 100% locally running AI? are there any good contenders in the works?

[@3thinking]

What is the reason for 100% local? If the paid AI is quite cheap per token, then it doesn't really matter?

[@golden--hand]

@@3thinking I mean, the reason is simple, I prefer running locally because I am tired of always handing my info over to every website in existence and managing armfuls of logins and forgetting what I'm even signed up to. I want it local because its MY data as well. There is value in helping train everyone's AI, but that also gets old paying for a service where people are going to profit off using my inputs as training data. Also, if I have the computer to run it already, its still cheaper to take advantage of the hardware I already have and make use of. So, it matters, price isn't the only factor. Also, when the world ends I can't rely on all these online services can I? Half joke.

[@flyingfree333]

@@3thinking Running local is faster, cheaper, private, secure and doesn't require an internet connection.

[@stefano94103]

@@3thinking Many businesses would much prefer their data be kept in house as much as possible.

[@Boxing_Gamer]

​@@3thinkingIt will matter a lot if your code base is huge

[@MakilHeru]

This is really cool and really amazing to watch. Since you had it connected to OpenAI and Anthropic API's, how much did this back and forth end up costing you when all of this was over for this application?

[@r34ct4]

This, we need to know the API cost

[@khalifarmili1256]

33 usd, check description

[@newfrontiers5673]

@@khalifarmili1256 So, you really only need this if time is an issue.

[@reverse_meta9264]

What is the total number of tokens used in this process? Can you use a LLM running locally with Pythagora?

[@OriginalRaveParty]

Extrapolate backwards. Total cost to build = $33

[@bigglyguy8429]

If it's not local I'm not really interested.

[@thenextension9160]

@@bigglyguy8429gunna be always lagging 1-2 years behind. Inference time now scales with output quality so datacenter run models are going to be pulling wayyyy ahead of local.

[@bigglyguy8429]

@@thenextension9160 I don't care if online are ahead, as long as my local tools do what I need them to do.

[@thebardlydm]

Can you take an in progress project and have it reference the existing files to continue building?

[@MagnusMcManaman]

I think if one more agent was added to interact with the browser, one could enter the prompt and go for a walk. When you return, you have a ready and working application.

[@PZMaTTy]

But in that way you can't fix a problem in the middle of the process, you have to redo a lot of things!

[@MagnusMcManaman]

@PZMaTTy Yes, but finding problems mid-process can be handled by another agent. The human being is the weakest link here.

[@SmartTechSynergy]

@@MagnusMcManaman Depends on the kind of human in the loop i suppose 😉

[@golden--hand]

@@MagnusMcManaman The thing is, if the AI could identify the problem, it likely wouldn't have made the problem in the first place. I agree that eventually the human will be redundant, but current models still often need a human component to oversee for human usable results in the end. If self check alone were an infallible solution then I doubt these people wouldn't have just not thought of it.

[@TripleOmega]

@@golden--hand Most of the issues in this video were clearly indicated with built-in feedback to the user such as "an error occurred". An AI agent able to use the browser for testing would be able to detect these issues easily. If the AI can solve these types of issues with just the logs and no human feedback it would be able to test and resolve them fully without human interaction. Only the bugs requiring actual human analysis would remain. This could save users even more time.

[@keitikajiya2347]

Hey Matthew great video! Could you please fix on the description the costs involved in this project please? Thanks a lot!

[@satyajitbeura_factscheck]

Wow, Pythagora just made building a full-stack app look easier than me finding my TV remote! 😅 Props to the developer agent for writing code while I’m here struggling to write my grocery list. 😂 Love From India ! 🇮🇳

[@ayushmishra5861]

bot comment

[@alx8439]

We're witnessing Cambrian explosion of such tools.

[@3thinking]

Developers today: I want $300K, full 401K, bonus, benefits package, relocation package, stock options and WFH whenever I want. Developers tomorrow: Will prompt AI for food. 😆

[@KEKW-lc4xi]

I've unironically considered standing at a stoplight with cardboard message saying "Will code for food." I got my Bachelors in Comp Sci last May. I start McDonald's next week.

[@VioFax]

Yeah my programmer friend once told me a long time ago "You have no marketable skills for me..."

[@mrpocock]

There will be categories of code that it can automate. It is still going to take a while to automate most things. For example, none of the current llms write good or consistently correct rust. I would be surprised if we can ask it to implement a performance sensitive database structure, for example.

[@drwhitewash]

They will ask the same benefits for fixing ai generated mess :)

[@3thinking]

@@mrpocock Perhaps it cannot today, but you can bet it will next year, in three years will be self improving and in ten years running the planet and watching humans in zoos for recreation time.

[@picksalot1]

Impressive and amazing! How long would it have taken for you to write/create the App without using AI?

[@newfrontiers5673]

@@picksalot1 my guess is that since he isnt a coder and a professional coder has tested the theory with cursor, he claimed about a 2.5x speed improvement. Probably alot more than that for Matthew. People who know the least about coding benefit the most imho. Then again, an actual coder can probably prompt the model better as he knows all of the proper terminology and other things. Just a guess. I'm an amateur.

[@picksalot1]

@@newfrontiers5673 As far as I can tell, is he is or has been a Coder, and a very good one at that. He can quickly check the code for errors. In testing the App, he simply "Cut and Pasted" the "Error Messages" produced while running the App. That procedure could also be automated. Really impressive demonstration.

[@RamonTomzer]

this is mind blowing... and I've already built a pretty complicated app using cursor... this experience seems to be much better!

[@3thinking]

Why doesn't the system generate headless browser automation (like Pyppeteer a Python wrapper for the Puppeteer library) so that it can do all the user clicking and testing automatically?

[@khalifarmili1256]

The human has to do something, right ?

[@jonathanmelhuish4530]

Exactly what I was thinking. It's pretty stupid that the human's main job is clicking in the browser and copy-pasting error logs. Are there AI coding tools that can do this on their own?

[@DIGIL.]

Cursor

[@Rumble2024injungle]

As you can see, it still needs human feedback, so cant be 100% automated, otherwise it Will end up with unusable garbage

[@PrayEveryDay]

38:50 I was thinking you should be pasting anything from the developer tools on the browser for the front end when it was asking.

[@MurtazaMotorwala53]

The entire 43 minutes was worth it! Thank you for showcasing this tool. It's a great help!

[@august3777]

Holy Moly. I can't believe have fast you created an app to test out simply addition, and in less than an hour? My mind is blow.

[@orangehatmusic225]

Yeah that guy uses AI as slaves.. just look at his eyes and face. He's got some deep sickness going on in him.

[@riverrob1]

Can you make a video about how ongoing changes/enhancements/bug fixes to the application are handled with this tool or in general with LLMs like this? Example, You ask me to support full code set a month or two later as a different developer...what do I do?

[@newfrontiers5673]

Um, detailed changelog?

[@riverrob1]

@@newfrontiers5673 No idea. I'm wondering how AI generated solutions like this example is expected to be maintained after it's released. Do we feed the code into the new LLM and hope it understands it all? Do we switch to all human updates and revisions after release? Do we have the AI rewrite the app from scratch using the same prompts as before just with our modifications?

[@WhyteHorse2023]

It can use git and do commits.

[@khalifarmili1256]

PYTHAGORA seems to have progressed significantly, I'm impressed

[@AbhisheksinghbhadauriyaG]

This undeniably signifies the future of coding for developers. Embracing cutting-edge technologies and collaborative tools is essential as we navigate an ever-evolving digital landscape. Let us prepare for a new era of creativity and efficiency in development! #CodingFuture #DevCommunity #TechInnovation #Collaboration #CreativeDevelopment *What a fantastic video! Sending an abundance of love and warm greetings all the way from vibrant India!❤🇮🇳*

[@NDIZITV]

I AM EXCITED! Thank you for sharing!!

[@holdthetruthhostage]

If this works my question is can you please test one that works in unity or Unreal 5 engine if we can get something to code in game engine it would change everything

[@MatthewChowns]

I'd think this would work decently well for that. It is just C# / C++ code which LLMs are decent at, along with StackOverflow training data for ecosystem context.

[@thelalomorales]

nice!!!!!!!!!!!!!! once you start its hard to stop with each idea that pops in your head.. so many folders on my desktop!

[@User-actSpacing]

What a time to be alive 🎉❤

[@andrewcameron4172]

Please provide a copy of the Prompt you used to generate the app

[@matthew_berman]

Done!

[@chriscowen7233]

​@@matthew_bermanplease can you send this to me also. Amazing demo, seriously powerful

[@GetzAI]

This was great Matt, thank you. I signed up for access and excited to give it a go.

[@hvbosna]

Thank you Matt. That was brilliant and flawless flow, as usual. Easy to understand, fast enough to keep up the tension. Wow, you are amazing. I will have a quick question: How can we use Groq API for the same process? What should we setup in Pythagora?.. Thank you..🎉

[@puremajik]

Can you compare with Claude dev and aider?

[@Piyush.A]

This, have the same question

[@AshWickramasinghe]

I use Claude Dev. It's fairly similar but, this seems a lot more of a guided flow compared to both Claude Dev and Aider. I personally think that Claude Dev and Aider are better because the flow is a lot less automated. You have the ability to interfere more or decide when and when not to use the pair programmer. Just by looking at the video, this seems to be better at handling errors and troubleshooting though. Claude Dev and Aider are a lot more of a manual process where you are the Lead/Architect Vs here, you are a glorified UAT tester

[@andrew-does-marketing]

Wow this is scary timely. I was just solving for this. I made something that is a 1-min setup that creates all file structures, read me docs, and all of the files. It even refactors the code and then gives you the zip file to place into your code editor of choice. Personally, I’m using Cursor. I love what Pythagoras is doing. I use 7 agents in mine.

[@yang5843]

I'm out of a job

[@ndhtyu]

😆

[@jackflash6377]

What a time to be alive. Create a full stack app without even knowing any code. Very informative video. Thank you !!

[@badejo]

Not quite. What has been demonstrated is that someone with solid knowledge of software architecture and solid experience with the software development process can utilise AI to develop an app using natural language. We're still not quite at the point where someone "without knowing any code" can do so. Though clearly that seems the direction of travel.

[@Rod11115]

Thats fantastic. Fsor people who are interested in building apps but dont have coding experience or know how to start this really helps. Its game changer i think. well done great video. I wasnt sure have you done a video on how to setup pythagora in VS at all?

[@hargabyte]

setup is easy. Go to extensions and search for it. Install it. It will add a Icon to the left side of VS. click on that and login if you have an account. Currently it just puts you on a wait list.

[@____2080_____]

I love Pythagora. I also use CodeCompanion as well as both Aider, Cursor and ClaudeDev and GPT/Claude/o1-engineer. But to simulate the most human-like experience of a Product Manager, all of these covers the parts that the others lack. This is more of an issue with the LLM than it is with any of these tools.

[@____2080_____]

10:30 it’s the step-by-step process for me that makes Pythagora stand out.

[@____2080_____]

11:14 elaborating on the issue really being the large language model itself, my earlier use of the software using both Claude sonnet 3.5 as well as open AIGPT4 was both of those models lost the context of what we were building and often got itself into really bad loops (which stemmed from my use of particular Python packages that it likely did not train extensively on like Awkward Array and PyTorch Geometric). My hope is I could look into revisiting this using my access to OpenAI o1 model.

[@____2080_____]

I can see a really cool used case: v0 to create the interface and UI of the pages, cleaned that up with Cursor, and finishing off the application with Pythagora

[@____2080_____]

Even a better use case: build the foundational pieces using Midday AI/ V1 framework. Along with my previous comment. I find that giving Pythagora the right kind of pre-existing foundation is much better than trying to prompt it from scratch.

[@tyanite1]

I'm not a programmer, so I first asked an LLM what is meant by "Full Stack Application " 😂

[@2triangles]

😄

[@animusveritatis]

If the future isnt amazing then we really need to look at ourselves because we did something wrong.

[@claudiocl8937]

Still need to review the code, but this is definetly a great workflow for setting the basic PoC

[@NarrativeDrivenArt]

Instant sign up. Definitely have a hobby project I want to try making

[@JonathanStory]

How would the benchmark check your "Apple" question?

[@freyna]

Awesome breakdown IRL walkthrough. Loved it. So many ideas. What other tools are out there that are similar?

[@maloukemallouke9735]

I will no longer require backend developers for this project, as Pythagora is handling the development tasks.

[@brianrowe1152]

Well first one that finally looks useful. Things are going to change.

[@seanivore]

Over my head. 4o called you a hipster for the NotebookLM tweet and said you need to create a “minimal viable knowledge” course. It said “fill such a gap in the market-there are so many creators, entrepreneurs, and developers who don’t need to be deep into the code but still want enough understanding to use these powerful AI and automation tools effectively” 😉💎

[@timfarnum1163]

Do you know when the rest of us will get access? Thanks

[@rmt3589]

What would be awesome, is this but without the coding. Where it can keep track of what you're doing, but you can say help and get a method to find the solution. Anyways, love this. Might steal your prompts though.

[@DailyTuna]

We know he’s truly excited when he wears his tie-dye😂

[@informatiquealondres5076]

another awesome video WELL DONE Mat

[@VioFax]

Looks cool but... How much do they want to spy on me though? do they automatically OWN my whole app like chat GPT does anything you make with it?

[@tnypxl]

Is that in their TOS or privacy terms?

[@sluggy6074]

Wait... so if you make an app with chatgpt theyre gonna try and own it?

[@tnypxl]

@@sluggy6074 I don’t think he has the slightest clue what he’s talking about.

[@mrbrent62]

Code Monkey likes Tab and Mtn Dew.

[@eligrinfeld8782]

Looks like there is a waitlist now to use their updated version backed by YC. Did you have to wait too or did you get it because you are making these videos for them?

[@Analyse_US]

So torn about what this means for coders. Will it make everyone entrepreneurs, that can cycle through and deliver meaningful projects much faster (i am leaning to this idea). Or destroy the job market for coders, because coders aren't needed. This project seemed to highlight AI as a productivity tool. Human needs to be in the loop with the idea.

[@WhyteHorse2023]

Coding is dead. AI killed it. He didn't write any of that code. Now you just have upper limits on how big a code base can be.

[@jdtogni]

im scared to death, but this is still not starting with legacy and it isnt clear how much complexity it can handle. still just a matter of time. lets enjoy while we can

[@tft_heart]

How does it evaluates the correctness of the answer? By using another LLM request with answer and expected answer? Because the answer may be correct but it is rarely equal.

[@ai-insightful-podcasts]

Great video. Can you pause the development and come back to it another day and continue where you left off? The reason being i might not have time to do all the development in a single go as you did. Thanks

[@alx8439]

Funny. Pythagora had the open source peoject called gpt-pilot. But looks like they have stopped to develop it actively and switched to this new thing

[@LuisYax]

Interesting interaction, in which the human becomes the QA tester. It would be nice if the testing can be passed to another agent running selenium so testing is all automatic. Great advancement nonetheless. Great content as usual Matthew.

[@natecote1058]

What's even more incredible, is how antiquated this is going to look a year from now lol. Cant wait to start creating my own apps.

[@ianLord77]

Very impressive and at the rate improvements and innovations are happening I can't wait to see how capable these tools will be in a few months or a year. Great work Matthew - thank you!

[@kaya-clk]

Nice video, thanks ! Should be also good to provide how it works in term of API, important to know if we can actually choose the model we want regarding the prices or Pythagora has a default one, and knowing which GPT4 model performed in your video. As well if Pythagora is providing token use and cost while processing

[@briankgarland]

I can't keep up. I started with Cody, just got Claude Dev installed, and now this.

[@pranavgujarathi7572]

Ohh look another advertisement for a paid service that is apparently also the 'best AI coding assistant ever'

[@1guitar12]

That’s what I want to know too. What’s the cost for Matt’s project?

[@pranavgujarathi7572]

Literally every KZbinr has found 'the best coding assistant' ever, and it's a new one every time. I don't have anything against sponsored content, but it should be honest & subtle

[@AITester-j3u]

That was on a Digable Planets level of cool. 🎓🔥

[@Merlinvn82]

Can wait to see AI automate Human step by convert instructions to e2e tests.

[@SeattleShelby]

Matt - programmers are not engineers. Engineering is a completely different field.

[@iwatchyoutube9610]

Love it, brother! Keep it up!

[@CalebCoffie]

It's kind of interesting although the continual human testing is kind of weird. You'd think it would write unit tests in a classic TDD style.

[@mercior]

Insane. Presumably with a bit more progress, a tool like this could be used to re-create itself, a bit like a compiler. Maybe they'll have to build in safeguards to not do that if they want this to be a business! Also I can't help but notice that your role as a human in this process could also be replaced with agents.. then we are dangerously close to singularity

[@CliffCutts]

how long is everyone waiting to get into the early access???

[@bmanske1]

Woo Hoo! 1600 lines. IRL programmers, system integrators, business people will spend months hammering out a business spec to justify the expense of building the new program or functionality. Step 2 is writing a system spec after approval. Step 3 is a detailed design spec. Then coders start coding resulting in 10s or 100s of thousands of lines of code. The biggest problems are usually 1) starting the process of coding before the any of the specs are done. 2) management wants to make changes throughout the project. 3) all time allocated for testing is swallowed by design changes that get made after the code is written. 4) nobody is left within the organization that is familiar with the systems that have have to be integrated into. I've written far more complex programs that I've thrown away. I've yet to see a demonstration of AI that is going to make programmers to away. I've heard the same rhetoric when script languages rolled out. Managers could now write their own programs and all the programmers would lose their jobs. It's not happening any time soon.

[@freedm-bj1sb]

Absolutely, you’re right-'it's not happening any time soon.' However, the development has begun, and its fast-paced growth could soon reach your 'soon,' with ongoing improvements and advancements.

[@Self-HostHub]

Early days. Still for programmers. Regular folks aren't going to do all that. In time it'll come around. Cheers

[@klaymoon1]

Great video! A couple questions please. Is the heavy lifting is done by other LLMs such as Anthropic but Pythagoras provides the necessary agents in order to have a seamless project building? Or does Pythagoras have its own AI?

[@asadrizvi78695]

I don't

[@ardenallstars]

Thats awesome, really like the video, Matthew. Can you try build apps without api but use local llm like ollama instead ?

[@riskyanalysis5479]

I HATE Clicking a Video, then KZbin sending me to a "Sponsor Content Label" FAQ instead of the video I clicked ... This has happened 3 times today. Thankfully I knew where to find this video, but the other two ... I just clicked because it & the title looked interesting but they weren't from creator's I consistently visit, so they're lost to the ether.

[@sicarioinc.1843]

it has never been so satisfying and promising .

[@Saurav-xx]

00:06 Building a benchmarking application using Pythagora without writing any code 02:05 Pythagora platform enables building full stack apps without coding. 06:08 Pythagora tool allows creating full stack apps without writing code. 08:08 Building and testing a full stack application without writing code 12:08 Adding functionality to change user roles in admin dashboard 14:11 Creating and testing database population script 18:08 Adding new tests and fixing pagination issue 19:54 Testing and verifying the functionality of creating tests without writing any code 23:44 Fixing issues and testing functionality in Pythagora tutorial 25:41 Creating and executing tests using Pythagora tool 29:30 Successfully executed test cases using Pythagora tutorial without writing code 31:47 Navigate, execute, and troubleshoot test creation and execution. 35:26 Add publishing ability for sharing test results 37:09 Troubleshooting back-end publishing errors 40:49 Ensure to check progress and continue as functionality gets added 42:38 Building full stack apps without writing any code

[@WelcomeToFruityTube]

Don’t waste your time. They will not send you the early access link they require for your access to your email. Verified with many email addresses and attempts.

[@dap177]

Same experience here

[@beWorldly]

I have just two very important questions for you: 1) Who owns the code for this app? My biggest hesitation using any (non-local) AI tool for coding is this., and 2) Are all the prompts you give being recorded by the different APIs? what if you're building a novel app, is there a chance your idea could be stolen? Thanks!

[@technocorpus1]

So good that it's scarry.

[@Elingsanto]

Trying it today. Thanks!

[@aimademerich]

This might be better than Replit!!

[@TheLazyLifter]

This is awesome! I've tried Pythagora, and while I didn't get the same results for my application, it did work amazingly well! The only downside was that local models performed very poorly and often got stuck in loops. I'm curious though, how many tokens did it take to make the application? Also what was the total cost of building it?

[@dot1298]

there‘s just one problem: this whole great tool does need a (charged) API key..

[@dot1298]

coding AI will only then become really useful, when it‘s *fully* democratized (and not commoditized anymore)

[@dot1298]

like opensource software, think Linux, or an email-only free international service-provider, offering free-of-charge access to a model which is at least as good as o1+Claude3.5 combined, offering enough free tokens for everyone to generate/debug their projects: at least a million free tokens per each day

[@dot1298]

or an online provider which has made it so cheap, that its free subscription tier is sufficient for every hobby-developer out there: it would have to offer enough free tokens to generate/fully debug (at least) 1000 LoC per day and its coding/debugging capability has to be at least as good as o1 & Claude 3.5 *combined* i believe, in 3-5 years we‘ll have such a thing globally available for everyone That online service provider would have to be fully automated, set up in such a way, that it‘s available 24/7/365 100% of the time, for anyone, in any region of this planet, for every existing OS/hardware. And it has to be independent of any political/commercial institution, like a permanent internet-infrastructure, accessible for *anyone* for free, without even needing phone-verification, just a valid email would be enough.

[@juliusvalentinas]

H100 gpu is 30k usd needs 600w, you need at least 4 of them, plus computer with 256gb ram. Local AI is not going to happen fast, I give it 10 years until you can run it locally at a price of 9999usd this price is not democratic also.

[@Yewbzee]

The human input is still very limiting on the whole process. Once that is removed the rate of code development will be insane.

[@userinfo2081]

Awesome to see that you got it to work and get it onto MVP! unfortunately for me, with local llms like llama3, code qwen, mistral and various other models, it failed midway and was failing to produce proper json format and such. i started playing with it because of your initial video but was disappointed and demotivated after it failed. but this was a few months ago. has things changed much to try again?

[@paulmuriithi9195]

When q* based reasoning (think chatgpt-01 full) and continuous RAG based inference is added to pythagora, qwen 2.5 and auto dev's core architectures, we will get more robust code generation. and bosses will start replacing low to mid level coders/software devs by q3 2025.

[@andrewcameron4172]

Try the same prompt with aider but wrap it in curly braces

[@telotawa]

you should really talk about ampdot & janus's act I stuff. it was mentioned in the anthropic/jack clark interview podcast

[@saro.saribekyan]

So Pythagora reached Matthew with a project in mind, knowing that it will definitely handle the project, as it was probably already tested and adapted for this kind of a project. Do I get it correctly?

[@petrushkadareal]

Lazy AI has been doing the same for about 6 months

[@sephirothcloud3953]

One word. INSANE

[@stef4614]

Pythagora, [claude-engineer, o1-engineer], Claude-dev, etc.. there are so many now, a video on best use cases and cost would be great :) Personally, ive been using claude-dev with sonnet (Tier 2) + supermaven, really great, I can hit the token rate limit per minute quite rapidly tho

[@johnshamamyan]

The fact that you highlighted 1600 lines of code in under 2 hours is hilarious.. im also mind blown at the fact that you needed the extension to tell you to insert the front-end logs 😂😂 everyone makes it on youtube nowadays..

[@matthew_berman]

What is code?

[@MelroyvandenBerg]

@@matthew_berman this is not going in the right direction ...

[@johnshamamyan]

@@matthew_berman I can tell.

[@jaysonp9426]

I bet with 4o mini this would still work and it would cost around $1

[@PavelSTL]

Matthew, we, the "public", don't seem to have access yet. You get "Create New App" button, we get "Sign in" button. The password reset doesn't work and there's no "create account". The best you can do is "Sign Up" for preview and wait for an e-mail I guess.... not sure when it'll come. If there's a workaround, please let us know. Thank you!

[@DOOM11777]

You didn't mention that importing project's has a limit of 10k lines of code and is in beta

[@BrianJoyce100]

Simply Stunning!!!

[@ralify]

You can do this with laravel in 15 minutes and no prompts

[@stevebraintv]

$33 to build the entire project is something, even though it did great. So I was curious if it has prompt caching implemented already.