Відео

I just received my invite to Devin. The cheapest plan offered "Personal (Devin Lite) users receive early access to Devin Lite for $50 / month, which includes 65 Devin Lite ACU / month built in. Additional Devin Lite ACUs can be purchased at our standard unit rate of $0.8 / ACU. Currently, each ACU is approximately equivalent to 10 minutes of active Devin Lite work." I'm having difficulty finding more information, but it seems to me, for $50 I get 650 minutes of computing. Looking at the lengths of time reported by Zack this seems like a very poor offer.

btw,i am still have no chance to use it,could you tell me how do you get this access to use?

Hi can you upload the repo for this please? Im stuck as to how you used the template

How does it compare to CodeCompanion ?

Have you tried Devika?

How install devon on win

Hey, I just finished watching you video about Devin AI. It's been a month since you uploaded it. Do you use it a lot? Is it actually helpfull? or it was just exiciting for a week and you didn't use it since. Just curious to know.

Can it Code games ?

I would love to see a video of Devin working in an existing project.

Hey Zack, your teaching skill is superb and you touched each & every small things. You have ability make difficult things easy to understand. But your video will not getting views enough. So I strongly suggest you to do SEO optimization of your videos after publishing. It will give you good. results.

Hey Zack can you post the repo for this project?

There were 2 things I wanted to see about Devin: How smart - which I guess is not amazing? I'm not sure how buggy the final product is, but it seemed to me like it ran into issues and required intervention. In the end, the main thing I guess is that it can do stuff, but if it's not as smart as Claude or GPT, then I might as well just copy and paste from the smarter llm instead of waiting for a dumber one automatically do it for me Basically, if you need to solve a coding problem, it does not seem like Devin is the way to do it How big is the context window - not sure from this I guess. Current problem with llm is that it's hard to have an entire project as context, so you have to find where to fix/add something and give them the info. I doubt Devin solved this, so I kind of want to see it given/generate a big project (at least bigger than the regular llm context windows) and told to fix something and see how it handles that. If those 2 things fail, then Devin is more or less a convenience thing - an AI that automatically runs what it generates, reads the error, and reprompts itself. I mean, these things already existed with AutoGPT and other stuff for a while now, so I'm not too invested, especially considering I can just run the llm generated code myself and give them the errors. So basically, it seems to boil down to convenience. As you said, it could take hours and give out a terrible buggy mess, but at least you didn't spend time on it. But if you truly want an actual product, it seems using smarter llms is still the way to go.

Thank you, hojestly wild how this is the only review on devin, the rest are just predicitions lol.

fingers crossed that I get in and try it out.

Why everyone who got access to Devin never shows real time interaction with Devin? Probably because it will revile how capable this ChatGPT wrapper is........

I'm the only one who doesn't have access?

Time to flip burgers now

I’m cooked

Hi, Zack! How quickly did you get off the waiting list?

So maybe it felt different using it, but it looked pretty horrible. I think most devs with Co-Pilot could do this infinitely faster. Not to mention remember the solution and re-impelement similar projects very easy in the future. The entire promise of Devin was a done for you software engineer. This looked horribly ineffficient. And if it needs this much input from a dev... Then why can't the dev just use co-pilot to implement it himself?

Chapters (Powered by ChapterMe) - 00:00 - Devon AI agent that claims to be worlds first fully autonomous 02:38 - Devons app turns world into museum 03:30 - Devon App builder with questions, planning, updates 05:20 - Android app asks users for help 06:08 - Deployment time 134 08:29 - Twohour CSS change to add features 08:51 - Devon walkthrough reveals power of commands 09:25 - Devon Excellent prototyping agent, impeccable UX 12:49 - AI software engineer Devons slow performance 14:59 - Devons powerful features, sign up now 15:22 - Lifted access for players

Are you sure it is not like the Amazon AI, a bunch of real people behind the scenes hahaha, it seems too slow for an AI

great video, the fan noise is slightly annoying though :-)

Interesting. I'm interested in really seeing how it handles complexity and things outside of its training set. These models have been trained by humans to cover all the basics of programming but beyond that the complexity of the work increases exponentially. I see it as a sort of Jevon's paradox. As programming becomes more available to the masses, there will be increased demand for experienced programmers to help guide these projects as they inevitably reach their limits. The world's top companies are already well aware of the limitations of AI and are pouring billions into training these models and I'm sure if Cognition Labs had some revolutionary way to increase the model's learning efficiency or somehow discovered a new way to approach model learning and training, they'd be in a bidding war with Google, Meta, and Amazon. Yet, this hasn't happened. We've seen some 175M of VC money thrown at it and the 'valuation' increase dramatically, but these are numbers in the sky. Experienced developers need to realize that models don't understand logic. They understand pattern recognition in terms of what humans determine they want to hear and predict what should happen next. I assume when Devin gets locked in a loop it just starts plugging things in to see if it works. Once if finds something that doesn't spit an error, it succeeds. Good for creating a nice little web app, but what about creating custom programs, queries, and results that are nearly impossible to replicate in the training set?

I'd love to see it contribute to an existing code base maybe try it on projects of different sizes/complexities

Awesome to see you're back, love the overview

Did this use gpt-4o?

Great overview. I really appreciated this video.

So if i wanna be developer I'm fucked,ai can do all for me

Thank you so much for impacting positively in people's lives..

very helpful man, thanks for making this for us!

I added also binding in the parent component like this: <TodoForm {addToList} bind:todoInput /> and that seems to work.

Hi, can you share the link to notion and discord?

great carry on!

Accidently discovered the streams. Great work.

wow nice content Zack

how do i find you on twitch? great content so far! I wish you would do something more real world than a todo app but that's cool for introducing DOM manipulation. I am at this point where I want to learn how a real front end workflow is like rather than a basic tutorial. Looking forward to learning how to consume APIs!

Hey I'm joining late but I can't access the discord server.

44:33 <> can be called angled brackets if that helps. As opposed to square brackets [].

Can I get the recording for day 3?

Thank you for uploading them on youtube zack!