Відео

Great video!

I have use Paid versions of both ChatGPT and Gemini and, I use it only for contnet generation. While the Sonnet is fast, the written contnet is still not at par (when it comes to emulating Human-like writing) with ChatGPT 4 & Gemini (maybe b/c of the obscene amount of data they used for the training). I am a Fan of the Artifact feature though. For me, at least, Sonnet writes better voice-over scripts than CGPT & Gemini. I do think Claude must be applauded here for the breakthrough. And I am going to use Claude more and more new future. I guess one size doesn't fit all.

claude 3.5 is my default llm - thank you fo the video:)

Great! Would've been great to see you use Claude for writing the API call and the app.

Thank you for the impressive video, even better if there is an on-premise solution.

Wow!!!

thank you a lot. any plan to take it to next level and explore creating a talking avatar on top of this, with open source?

hey can you make one using reactjs?

nice video. thx a lot. but wenn ich close the server. all my data are gone right? all the learnings?

It would be nice to dive deeper into the System Messages and how these impact the Result I am struggling with Infinite Loops. I try to create an IT Service Deskagent who Interpret an email and give suggestions. A skill would be to interact with our jira Service Desk Solution and create a well formatted ticket

The voiceflow interface has changed significantly, and it is very difficult to replicate what you have in the video.

Real GPT 5/6 level intelligence if anyone wants an extensively tested 10 x vision capabilities 10 x smarter outputs for chat GPT i figured out something crazy, just remove the spaces here Its called Smart Vision image/text analysis Or visit my channel description for the direct link (Paste your own custom instructions for a superior smart chat aswell It can put text into images, solve highly complex math and physics problems even reasoning images and so much more This is not a trick i’ve extensively tested to get these answers first try, read **IMPORTANT** in the GPT’s conversation starter

Thanks for your tutorials, they have been very helpful and informative. You mentioned that it's better not to send a json to ChatGPT as "it can do less", and you advised to output the data to string. I just want to understand if that is still the case, and why is a String the better option. I don't mind either way, I'm learning so just interested to know why. Thanks again for the good tutorials.

I need something that starts at a more basic level. What do I do to get the "autogen_studio" prompt? I'm lost after 1:20.

yes please continue this video with more details!

Unlimited Memory????But I'm aware of that's not possible every single AI language model I've ever interacted with seems to have a very limited long-term memory majority of them memory dump after about a week or three days. The ones on platforms like replica as an example have some memory but not much. There is even been a lot of discussions in UA-cam videos about as far as I know there's nobody out there that the AI has any real permanent memory to speak of to any real extent there's always a pretty small token limit on the permanent memory

What do these companies charge for API keys?

Can you use a local model?

Isn't ElevenLabs very expensive?

Memgpt is slow as it consists of agent . Also elevenlabs is free 😢 please give a free alternative ❤😅

Awesome project. Will have to build this for the wife :D

Excellent video, you are amazing! I have a question. In AutoGen, there are the TeachableAgents, which you showed in a previous video. I want to create an assistant like Alexa or Google, but using an LLM behind it, to give it a touch like JARVIS by adding tools such as: - control of home assistant - internet search - managing my schedule - alarms - among other things My question is, what would you recommend more? Using MemGPT or the TeachableAgents? Best regards.

This is not free. You can not use OpenAI for free. On a free openai account, with the free key, if you try to connect you either get a connection refused error or an error that says you exceeded your current quota.

Thanks mate! ❤

Thanks for the Video, I got it working from scratch. It's pretty good. Had to add a line in the def play.audio(file_path) to get her to answer again. Put this at the end.... pygame.mixer.music.unload() Like so. def play_audio(file_path): pygame.mixer.init() pygame.mixer.music.load(file_path) pygame.mixer.music.play() # Wait until the audio is finished playing while pygame.mixer.music.get_busy(): time.sleep(1) pygame.mixer.music.unload()

Nice video! Is there a link to the source code? TIA!

This is great. Did you automate the final version of the meeting notes as well or cleaned it up yourself? If automated please show that as well.

_Dr. K has entered the chat._

integrating this solution for the same use case used in 50 min master class solution you did with VoiceFlow would be great.

go outside!

LM Studio isn't open source

call it "tsundere" gf for marketing purposes

What's the max amount of lines you can use when describing the character in the python code, on your system?

Everyone need an evil gf in thier life

As if you don't have enough of those walking around in the real world.😮😮😮 Wtf is wrong with people? You get something with so much potential and the first thought is how to make a corrupt and perverse version of it.

Hey! Great content, yet I couldn't reach the source code of the web app part. The links below expired or not work. Can you provide me a new link?

Such a weird idea. This novelty alone got me to watch.

Hey thank you for that amazing code! I have a problem. The second moment i ask a question the output.mp3 file gives me an error. PermissionError: [Errno 13] Permission denied: 'C:\\Users\\Mauricio\\Desktop\\Gpt4o GF\\output.mp3' What could be the solution?

This tutorial is a so dated compared to others on yt...

I really need a follow-up where you ask it some technical questions. Or give it a task to accomplish. You told it not to do small talk, then you only did small talk.

*69 Comments!* Haa *_sorry_* I guess I messed that up for us *ALL!*

Will do this project, add a function of likeablility score which improves with good interactions and the attitude AI will change with it. Becomes warm/vulnerable/tsundere etc.

She said "data" instead of "data"

LMstudio is proprietary software, it is not open source.

Does she take off with half your compute and storage and demand you fund upgrades for the rest of your life?

Irish AI girlfriend?

Y tf would I want to do that?

Well that conversation won't go far. It will cut you off right away every single time 😂 also the point being?

This is one of those things that you don't wonder if you can do it, but if you should do it

I came here just for the coments