I just discovered aider yesterday and less than 3 hours I build sign-up flow for my application. LLM is Claude 3.5 sonnet. It costs me around 1 dollar to complete all application. Google OAuth2.0 integrated, tests are written, db integration done. So good. I've never did sign-up part of the application before but it is goooood!
@ack0x068 күн бұрын
I would like to sincerely suggest anyone who uses this wonderful tool to install it using `pipx` instead of just globally installing it with `pip`. This way, it is installed safely within its own virtual environment while still being available anywhere. `pipx` can also upgrade it without either messing with or being hampered by your other (user) globally installed packages, which is a big plus for such an important tool.
@JoshuaVial8 күн бұрын
Great sugggestion
@luisavila842129 күн бұрын
BUG: Error "edit does not conform to the edit format" stucks Aider in a loop, cannot continue The LLM did not conform to the edit format. aider.chat/docs/troubleshooting/edit-errors.html # 1 SEARCH/REPLACE block failed to match! ## SearchReplaceNoExactMatch: This SEARCH block failed to exactly match lines in lib/main.dart <<<<<<< SEARCH
@flethackerАй бұрын
this is how programming should have been from the beginning
@werthersoriginalАй бұрын
Well F**k me lol... Coqui is shutting down. Thank you for all your support! ❤
@MaisonierАй бұрын
What about now with DeepSeek-Coder-V2 vs gpt 3.5? great video, liked and subscribed.
@konstantinrebrov675Ай бұрын
Can we write a prompt in the terminal, and then have the AI generate a command based on that prompt? It would be useful for especially long commands, where you pipe the output of one program into the input of another program, parsing data such as log files for example.
@LearnCodeWithJVАй бұрын
yep, have a look at open interpreter which is designed to do just that.
@konstantinrebrov675Ай бұрын
Hello sir. I have a list of names of the VSCode extensions that I want to download and install. Can I use Open Interpreter to, just based on the name of the extension, find it in the VSCode Marketplace, download the *.vsix file, save it onto my USB drive, then run the command to install it, and also take the description of the extension from the VSCode Marketplace, and download a PDF of that extension, with the same filename, and save it so that I know what this extension does and how to use it?
@LearnCodeWithJVАй бұрын
maybe, it's the sort of task I would break down into steps - the 'find and install from vscode marketplace' would be the bit I think it would struggle with the most. Personally I would make a small script to do the hard part and then you can test it in isolation and use OI to integrate it with other shell commands if you want.
@timemasheen50312 ай бұрын
This is an excellent video on these three TTS, thank you for your work JV.
@someuser41662 ай бұрын
i wonder if there's any way to run the game voice thing though CLI. im bulk translating all the voice lines in an already existing game to learn a new language but theres thousands of lines so i dont want to copy paste each one by hand and download and name them... also my GPU is from like 2013
@MistakingManx3 ай бұрын
What GPU do you have? As reference for just how hefty the last one is.
@LearnCodeWithJV3 ай бұрын
RTX 3060 so pretty light weight
@MistakingManx3 ай бұрын
@@LearnCodeWithJV I have the 4060TI, would that heavy one run well on mine?
@giacomosiiii4 ай бұрын
Tortoise sounds great but I was NOT ready to hear the "deniro" model sound British instead of Bronx LOL
@user-ow9tk2vc8s5 ай бұрын
Thank you very very much. You helped me a lot. This is what I was looking for.
@ForTheEraOfLove5 ай бұрын
I believe the review, demo and installation in that order are the future of video reviews. Good on you!🥇
@LearnCodeWithJV3 ай бұрын
thanks
@javi_park6 ай бұрын
Great video Josh. would love to see an update video on Aider! just tried it this week and it's quite mindblowing.
@LearnCodeWithJV6 ай бұрын
yeah, lots has changed since the original. It's on my list.
@javi_park6 ай бұрын
can't wait!@@LearnCodeWithJV
@pablomax93766 ай бұрын
Coqui-ai shut down in the meantime. The website UI I mean, not the repo.
@LearnCodeWithJV6 ай бұрын
yeah, it's a shame they couldn't make a go of it
@user-vk5lj3ok4m6 ай бұрын
Well presented overview of some of the things happening in AI, thanks
@mdsalahuddin28416 ай бұрын
any opinion on Tacotron 2?
@StormWolf016 ай бұрын
All of this is amazing.
@paritaistudio2067 ай бұрын
Thanks for the content! i enjoyed a OpenAI / ChatGPT video for the first time in months, simple and informative, it's really appreciated. I've been in the search of replacin the OpenAI API token with running my model locally and directing my apps to it with 0 luck. All i want is to run a chatbot on wordpress with a local LLM usin ollama. Good thing dreaming it's still free :)
@LearnCodeWithJV7 ай бұрын
Nice, the good news is the open models keep getting more performant!
@MelroyvandenBerg7 ай бұрын
I which I can easily use ollama together with the power of text-generation-webui project.
@goonie798 ай бұрын
Great tutorial. Is there a method to use Ngrok and Litellm on the Google Colab side and then connect from local machine to it? This would make Open Interpreter powerful for any machine.
@LearnCodeWithJV8 ай бұрын
Probably. I know google colab doesn't like running servers and prioritises interactive notebooks so I would guess it's a bit of a moving target. I've seen a bunch of stable diffusion notebooks they've disabled but the Ngrok + Litellm combo sounds simple enough that it would be worth a try.
@AdrianJames818 ай бұрын
Enjoying the videos JV, would def watch deep dives!
@killianlucas8 ай бұрын
Extraordinary video JV, great demos. And thanks on behalf of all devs building on Open Interpreter for making that commit from 8:46 which brought the size of the repo down by over 20x. Brilliant!!
@LearnCodeWithJV8 ай бұрын
My pleasure. It's great to see all the progress on the project, you're writing code a lot faster than I make videos :)
@rich.fortune8 ай бұрын
Thanks for sharing JV! Can you share your local setup too (in the vids or in a linked video) so people like myself can get a realistic measure of what we can achieve at home. (you touched on it a bit in this video, but any additional info would be :chefskiss:
@LearnCodeWithJV8 ай бұрын
I get a few questions every now and then when I run local stuff but the setup isn't that interesting and I don't know if I'd have much more to say than list some specs. NVIDIA RTX 3060 with 12 GB is the main driver of how well the local models perform. For the rest I just run Windows Subsystem Linux on a i9 with 3.3ghz and 64GB memory
@SR-zi1pw8 ай бұрын
Nice
@LearnCodeWithJV8 ай бұрын
Thanks
@mohsinsheikh24809 ай бұрын
Thanks great ! Whats the configuration of your system?
@LearnCodeWithJV8 ай бұрын
NVIDIA RTX 3060 with 12 GB is the main driver of how well the local models perform. For the rest I just run Windows Subsystem Linux on a i9 with 3.3ghz and 64GB memory
@forestpeoplemushrooms52679 ай бұрын
Thanks for the video! Got the model working in colab webui but the cloud flare link is broken somehow. Thanks for all your work to make this video. Cheers
@LearnCodeWithJV9 ай бұрын
Glad it was useful
@NullifierMotion10 ай бұрын
Thank you for quick and helpful update on Ai!
@LearnCodeWithJV10 ай бұрын
Glad it was helpful
@stevecato10 ай бұрын
Tortoise is good but very slow. Is the reason for this that it starts over from the voice training set every time? You mentioned the ability to save an intermediate vector of the voice - could you cover that in a video and whether it improves the speed. Thanks.
@LearnCodeWithJV10 ай бұрын
yeah, it's name is apt. I've seen a few derivative projects kicking around which are claiming significant speedups. I'm waiting until I find one with good voice cloning and multi lingual abilities and a commercially available license to do the follow up.
@Yeeeeeehaw10 ай бұрын
Great video
@LearnCodeWithJV10 ай бұрын
Thanks!
@officialp28310 ай бұрын
What is your hardware specs??????
@LearnCodeWithJV10 ай бұрын
i9 3.3Ghz with RTX 3060 using wsl2
@jamiediromero501610 ай бұрын
I see no Advanced Editor on the coqui web-site in menu
@LearnCodeWithJV10 ай бұрын
I remember it only showing up some of the time and being disabled when a voice was rendering. Have a half memory of it only working for built in voices but I can't recall.
@oliverli963010 ай бұрын
open source for the win!
@LearnCodeWithJV10 ай бұрын
indeed, people are building a lot of cool stuff.
@99NOFX10 ай бұрын
It was only a few hours before watching this I chose 'Oi' to address my AI
@LearnCodeWithJV10 ай бұрын
I don't know if I could handle it as a wake word, but I love it in the command line.
@99NOFX10 ай бұрын
@@LearnCodeWithJV an Ozzie intelligence.
@abiramyk351410 ай бұрын
What are the requirements are they using
@LearnCodeWithJV10 ай бұрын
which project were you referring to?
@neur0mania10 ай бұрын
hi,Do you know how to solve this problem "echo "Hello, World"?
@LearnCodeWithJV10 ай бұрын
It looks like you don't need the " in front of the echo
@Care2WorldBuild10 ай бұрын
I've used Powerline to customize my terminal prompt. What customization have you set to get your terminal that way?
@LearnCodeWithJV10 ай бұрын
I'm using oh my zsh with the bira theme and hte git, node, tmux, docker plugins - nothing custom.
@Care2WorldBuild10 ай бұрын
Has anyone already forced a push of the history cleanup or if not possible, can you upload your repo so we don't have to deal with the venv and whl commits? We can then grab the latest changes from the main repo without having to deal with that history I hope.
@LearnCodeWithJV10 ай бұрын
Not yet, I created an issue that hasn't had any action on it - github.com/KillianLucas/open-interpreter/issues/214 - feel free to add your voice there if you'd like them to prioritise it. You can get access to a (as of now) version of main with the files removed at github.com/joshuavial/open-interpreter/tree/clean-git-history - you shold be able to rebase it off the official repo as needed, but as soon as you add their remote to your repo and pull it down you'll get the large history anyway.
@Care2WorldBuild10 ай бұрын
@@LearnCodeWithJV Thanks for that branch. Yes I hope they resolve the 214 issue over having others wanting to git cherry pick.
@killianlucas8 ай бұрын
Merged! Thanks to JV :) @@Care2WorldBuild
@markusboremski264310 ай бұрын
I am stunned by the possibilities of OI. Maybe as a feedback for the VideoCreator: I am not a native speaker. I really had a hard time to understand what you said. Mostly due to your cutting in the middle of sentences and fast speach.
@LearnCodeWithJV10 ай бұрын
Thanks for the feedback, talking slower and clearer is something I'd like to work on.
@HaseebHeaven10 ай бұрын
Open Interpreter is cool but API usage is high.
@LearnCodeWithJV10 ай бұрын
yes, it is something to watch. I found that the local models were good enough for some simple tasks.
@eirikgg10 ай бұрын
@LearnCodeWithJV I have created something very similar, been working on it for a while, and changing it to GPT 4 made it a lot better, but also alot more expensive. And for me its that i need the conversation to get the results back from every command it executes so it may stop its task or change the task objects. There is a huge potensial here when combing it with better prompting (tree of thoughts or graph) but that would make it even more expensive. Also connecting it up to a credetial db for access to other system that what it executes on. But trusting it to perform something in production is not there yet, it would have to be supervised by a human.
@quickcinemarecap10 ай бұрын
You earned a space in my subscription list
@LearnCodeWithJV10 ай бұрын
Thanks!
@jdsguam10 ай бұрын
I installed it last night for the first time and I'm am shockingly amazed at how this works. Just asked it to scan my images and delete duplicates no problem. I asked it to create a short-cut on my desktop to automatically open and interact with the terminal - no problem. I asked it to convert some Stable Diffusion Images into usable Icon files and it did so flawlessly and then I asked it to make the square icons into round icons and it did so within seconds. I played with it for about 4 hours or so and it costs me about $1 per hour, give or take, with OpenAI.
@LearnCodeWithJV10 ай бұрын
Yeah, it’s amazingly useful at miscellaneous admin tasks. Nice use cases.
@MAILQS11 ай бұрын
Awesome thanks JV!
@LearnCodeWithJV11 ай бұрын
My pleasure, hope you find it useful.
@TheNativeTwo11 ай бұрын
Unfortunately “tools to measure bias” are really just tools to give models a leftist or woke bias. I have seen it in many AI, including chatgpt.
@LearnCodeWithJV11 ай бұрын
Maybe, I think there is a big difference between measuring bias and training models for certain outputs. I think it should be possible for quite a broad group of people come to agreement about what an accurate measure would look like, while I suspect there will be a lot of differing opinions about what the desired output should be.
@TheNativeTwo11 ай бұрын
@@LearnCodeWithJV The problem with bias is more fundamental than that. The measurement tool itself will have bias. No broad group can create an unbiased tool. Think of it like this, let’s say they create a tool and make it perfectly unbiased by today’s standards. Will people 500 years from now still think it is unbiased? No they will laugh at what we considered bias. 500 years is a huge divide, but we don’t have to go that far. Just take any two opposing groups of people today and you will get wildly differing opinions on what is bias. I work in Silicon Valley as a software engineer. My coworkers and management are extremely left biased. There is no way that won’t make it into the tool. Just asking the question about “female nurses representation” vs “50/50 representation” is already left biased, and we are just asking the question and haven’t even gotten to the question yet! And if a person can’t see that, then that is their left bias blinding them to their own internal biases.
@lrkx_11 ай бұрын
Personally I’d like to see more coverage of open source llm’s; commercial, closed source nanny-like llm’s are pretty awful if you like extra spicy mayo recipes. I’m looking at you, Llama 2! :)
@LearnCodeWithJV11 ай бұрын
Noted - you might want to checkout openrouter.ai - they are an easy way to get access to a whole bunch of unfiltered models without worrying about self hosting.
@chrisBruner11 ай бұрын
Just the video I was looking for. Your eyes can be a bit brighter now, I've subscribed!
@LearnCodeWithJV11 ай бұрын
They are indeed. Thanks!
@danlewis_bamboocreative11 ай бұрын
Hey JV, your right regarding cursor being a fork. > Cursor is a fork of VSCode. Import all your extensions, themes, and keybindings in one-click. Keep your code local With local mode, we store none of your data in our servers or logs.
@LearnCodeWithJV10 ай бұрын
Have you played with cursor at all? It's still on my list to give it a kick - the way it handles docs looks to be the most interesting piece
@DanAlexiLewis10 ай бұрын
@@LearnCodeWithJV I’ve been using it for a month. I found 2 things: 1. It worked a lot better with tabnine/copilot + vim. 2. I like some of the ui simplifications they made to vscode Regarding the chat functionality, so far I haven’t found it hugely useful. I’d ask it to explain stuff or bring up the docs for something. But it’s not as in your face valuable as tabnine/copilot
@gfhdlsk11 ай бұрын
You could update that mimic3 is "moved" to piper and is still improved by the same author
@LearnCodeWithJV11 ай бұрын
I wasn't aware of that - thanks for sharing, Updating the description now.
@gfhdlsk11 ай бұрын
I don't agree with the title, for me production ready would also require privacy. Any serious company won't allow programmers to send their proprietary code to OpenAI's servers. This assistant is more like open source/private projects "production ready".
@LearnCodeWithJV11 ай бұрын
That's a fair point, there are a lot of companies that won't allow folks to use OpenAI apis. I expect that will be solved reasonably soon though as companies stand up enterprise friendly AIs or the open models get good enough with fine tuning. The main thing I was surprised with Aider was that the quality of the code + the dev workflow was good enough for production use.