"Next Level Prompts?" - 10 mins into advanced prompting
Вставка
- Опубліковано 9 чер 2024
- Some advanced prompt engineer framework that give you a lot more control of LLM to deliver consistant results at scale...
🔗 Links
- Follow me on twitter: / jasonzhou1993
- Join my AI email list: www.ai-jason.com/
- Github repo: github.com/JayZeeDesign/promp...
- My discord: / discord
- FlowGPT: flowgpt.com/
- GPT prompt engineer: github.com/mshumer/gpt-prompt...
⏱️ Timestamps
0:00 Intro
0:20 Microsoft guidance
0:50 Setup
1:40 Control prompt output structure
2:07 Multi choice option for LLM
2:57 If condition in prompts
4:20 Case study: Generate structured email
5:51 Case study: Generate charts
7:48 Case study: Generate images
9:07 FlowGPT
9:55 GPT Prompt Engineer
👋🏻 About Me
My name is Jason Zhou, a product designer who shares interesting AI experiments & products. Email me if you need help building AI apps! ask@ai-jason.com
Blog: www.ai-jason.com/blog/prompt-...
#prompting #promptengineering #prompts #prompt #promptbuilding #promptformidjourney #chatgptprompts #chatgptprompt #promptengineer #gpt #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #largelanguagemodels #largelanguagemodel #chatgpt #gpt4 #machinelearning - Наука та технологія
Bro, how is your English so much easier to understand than many native english speakers! I'm blown away by the clarity and easiness in your explanations making everything so easy to understand. Appreciate you fam.
E-nun-cia-tion
Truly one of the best AI channels on the internet right now. Clear, concise and leagues above the repetitive content most creators put out. Thank you for the insights.
Jason, I sincerely wish you success in all that you do and pray for the health and well-being of you and your family. Your presentations exude a genuine joy in sharing what you have discovered and seeking feedback from those of us who are seeking to utilize this technology for good. That's just from my heart to yours. That said, I must admit that my wish is partly motivated by my hope that you will not stop providing what I find to be the most useful and concisely presented AI content. Thank you for being you and doing you.
nailed this one ☝️
i was like “here we go with another prompt video”, boy was i wrong lol. this was definitely next level 👏🏾
i was subscribed since the very beginning, but i cannot believe how far this channel has come (and is going). i've truly gained and learned so much from you and i cannot thank you enough.
Hah thanks mate! You were my first comment I believe ;) meant a lot’
Bro just packs in so much value in each vid. Damm
Just found your channel from your finetuning tutorial. Gold! Thank you for sharing. Very clear & concise.
bro your channel is the best on UA-cam right now..well done
Hi Jason, your content is great! Please keep it coming, very much appreciated.
thanks a lot. Your vids always have the best examples and delivery.
Super useful thanks Jason 🙏🏽
Great video Jason 🔥, am learning a lot from you. I really liked the tools you showed at the end too, will be great if you created a video showing all the amazing tools you use and quick overview how they help you.
Keep going, you are by far the best from all the AI UA-camrs....100% knowledge, 0% Bullshit.
Awesome video on Guidance. Been looking for something like this. Thanks.
I think a library of templates or use cases will be useful.
_TREMENDOUSLY_ *helpful*
Thank u, very helpful. Just as time I wonder how some prompt in FlowGPT so powerful, u gave me the answer!
Woahh, didnt know Microsoft guidance before, the ability to get control of output is super handy!
Excellent information. I will set my sights on it asap. Thanks!
Keep up the good work Jason!
each of your ai videos are pure gold. Such amazing content, not the AI influencer crap
Great content Jason! Thanks
Great info! Thank you so much!
Amazing Jason thank you!!
This is ... so helpful!
Dude you are my hero!
Great video as usual
Great video!
Great video brother ❤
Awesome, gave me a lot of ideas.
Could totally be packaged as a web product
Thank you for this video
Really cool man 🙌🙌🙌
Thanks brother. ❤
just helpful tremendously LOL!!! thank you so much bro as always!! I feel like using the guidance technique is kind of an alternative for fine-tuning. As you said previously, fine tuning is a just way to teach the behavior of the model. I am currently building up a tool for retrieving data from Google Analytics 4, which requires GPT to understand and extract info from users' queries and eventually format corresponding info into code snippets so as to be used later as part of google analytic API. and I was initially trying to do this using fine tuning , but after watched this , i feel like i better give a try for guidance first lol, it just gives crazy control over output format
Awesome content 🤌Keep going.
THANK YOU
Thank you soooo much
This video is literally fucking awesome!!
Really good 🎉
DUDE!!! very cool!
More please!
So useful!
Thanks!
Could you please make a video on LMQL? Also how do you integrate function calling in Microsoft guidance? Thanks for doing this.
Hi, thanks for the content.
What is the basic setup you need to run this examples?
You running guidance on VS Code was it though a plugin?
wow, i enjoyed alot! gonna subscribe you gladly
thanks
Thanks for the video Jason. How is this different than the OpenAi functions?
Great Video 👍I have on very general question: At the end of the day everything you do in e.g. "guidance" is translated down to a prompt right? So if you define options (e.g. "yes" and "no") that only means that there will be a part of the prompt that asks the model to please stick to those options, right? So if the model actually really does this is not guaranteed, right?
Please tell us in future videos about RAG. Thanks
Thanks! I'm thinking how we can use this 🤔
Also, emailed you and DMed you on Twitter.
Thanks mate, Responded!
Good video. I wonder, how did you get prompts from flowgpt? seems not to show the actual prompts anymore
Gold nuggets!
This was great! Is there a javascript alternative to Guidance?
I was wondering this.
Thank you for the video! Tbh I had to laugh so hard when you said "the tacos taste pretty shit" 😂 it came so unexpected
Hahah nothing personal against taco! 😂
Hi, Its good video and im having trouble when im trying with my own
When I try examples with the GPT-4 and GPT3-5 models, I get responses like this: "The best thing about the beach is {{~gen 'best' temperature=0.7 max_tokens=7}}". Are there other models that can be used, or is there something wrong with these?
can you use guidance with open source llm?
I couldn't find many syntaxes you used in the video on GitHub.
Is it just making up syntaxes and the GPT model interprets it?
Because I cannot find information on conditional logic in the repository.
thanks Jason, is this better than Langchain, when you recommend to use that over the other
Probably when you need to use tools like a vector database.
Would love a deep video on how guidance works
So the way it works is actually pretty straightforward, it does a lot of leg work of output parser
can we use it with langchain@@AIJasonZ
A friend is cool
Does this tool need an openai key or must pay money for any services? Thks mate
Where is the resource link for guidance?
How about OpenAI custom function calling?
Was the title for this video generated by LLM as well? :D
For a total no-code/flowise user is there anyway for me to apply this?
I need a more specific tutorial for a email response prompt that works well with any kind of email.
1:23 instead of a counter-argument it resulted in a statement of agreement & elaboration. Or am I mistaken?
First like!
May i ask what is inside the .env?
man you did like 5 videos at once
why i use don;t work , but just show template, can u fix that ?
Oh yea if it shows templates, that means there are errors; feel free to share your guidance and I can see what went wrong
@@AIJasonZ thank you , I upgrade version, and fix that (before i get error when i use with gpt-4, or gpt-3.5-turbo-16k,..)
My tacos are delicious!
How does this compare Nvidia guard rails?
Guard rail is similar but I found guidance is simpler to use
@@AIJasonZ preciate it love the videos
To anyone who knows basic programming, those "templating frameworks" don't make sense.
Why don't you give examples using open-source models, are you funded by OpenAI?
Simply because openai is cheap and easy to use
For me the quality of response in current open source models seems too poor to build business solutions on. I hope they get better (or that my perception is outdated 😉)
Hey, i am working on my personal project, which detects AI generated content ( tells in %age, how much input is human generated) I am confused, and really seeking help, to know how to achieve this, like what to train my model on? I am also taking into account perplexity for better detection!
smith langchain hub