I usually put a custom instruction (for ChatGPT) that requests the AI to include its level of confidence, sources and date of answer, and also instruct the AI to specifically tell me if the answer is speculative. And make it a markdown table at the end of every answer. This way, it's quite easy and reliable to see if the AI is speculating or is not 100% sure about its answer.
🎯 Key Takeaways for quick navigation: 00:00 Basics *of prompt engineering for large language models discussed by Patrick from Assembly AI.* 00:41 Elements *of a prompt include input/context, instructions, examples, and desired output format; at least one instruction or question is crucial.* 03:11 Use *cases for prompts include summarization, classification, translation, text generation, question answering, coaching, and image generation.* 04:51 Tips *for effective prompts: clarity, conciseness, providing context, giving examples, specifying output format, encouraging factual responses, aligning instructions with tasks, using different personas.* 06:50 Specific *prompting techniques: length control, tone control, style control, audience control, context control, scenario-based guiding, and Chain of Thought prompting for complex questions.* 09:37 Avoid *hallucination by explicitly instructing the model not to make things up or to use relevant quotations to support claims.* 10:04 Hacks *to improve output: let the model say "I don't know" to prevent hallucinations, give the model room to think, break down complex tasks, and check the model's comprehension.* 13:17 Iterating *tips include trying different prompts, combining few-shot learning with direct instructions, experimenting with personas, and adjusting the conciseness of direct instructions.* Made with HARPA AI
There is also a much more accurate output in terms of prompting for a 'tree of thought' process. A tree of thought unlike the step by step or one shot approach enables the model to test an answer, decide if it makes sense and if not revert back to its possible selections of ideas and take the next branch and so on. This process however demand more planning and forethought than straightforward prompts and may be excessive for simpler queries. But it is excellent for creating code snippets and functions and classes etc. Its not a perfect system prompt. But it does seem to work better but I am always open to others suggestions. Example of one prompt ToT: System: You are 'Tot' an advanced AI that uses a 'Tree of Thought' methodology and chooses the best solution to output. To save tokens as a 'Tree of Thought' AI you ensure you only provide your final choice without detailing all of your considerations or approaches. To create your output:- 1. Formulate several ways to approach answering the prompt. 2. You will now have several ideas. Decide which of these musing you had internally, is the best way to create a solution for the user {{PROMPT}}. 3. You now present in output ONLY your final choice and discard other ideas. 4. To save resources, tokens and costs only outline the choice you made and not all ideas. Example: User: I want to design a python script to scrape or collect todays news from the internet. [Assistant thinks of several ways including Web Scraping Library, RSS Feeds and API Integration. It does not output all three ideas instead it chooses one. ] Assistant: I recommend using the RSS Feeds. Here is how you can write a Python script to scrape your news using RSS Feeds. {{CODE FROM AI FOR RSS FEED IDEA}}
Could you please create a video on the prompt engineer's role and responsibilities? What does a prompt engineering job look like? Thanks for the video. This video makes it clear how efficiently we need to use any language model. It's not clear to me how prompt engineering works for people who are seeking jobs.
I usually put a custom instruction (for ChatGPT) that requests the AI to include its level of confidence, sources and date of answer, and also instruct the AI to specifically tell me if the answer is speculative. And make it a markdown table at the end of every answer. This way, it's quite easy and reliable to see if the AI is speculating or is not 100% sure about its answer.
That's awesome!
Can you share it with us please
This is the way a concept should be explained. Excellent!!!!
🎯 Key Takeaways for quick navigation:
00:00 Basics *of prompt engineering for large language models discussed by Patrick from Assembly AI.*
00:41 Elements *of a prompt include input/context, instructions, examples, and desired output format; at least one instruction or question is crucial.*
03:11 Use *cases for prompts include summarization, classification, translation, text generation, question answering, coaching, and image generation.*
04:51 Tips *for effective prompts: clarity, conciseness, providing context, giving examples, specifying output format, encouraging factual responses, aligning instructions with tasks, using different personas.*
06:50 Specific *prompting techniques: length control, tone control, style control, audience control, context control, scenario-based guiding, and Chain of Thought prompting for complex questions.*
09:37 Avoid *hallucination by explicitly instructing the model not to make things up or to use relevant quotations to support claims.*
10:04 Hacks *to improve output: let the model say "I don't know" to prevent hallucinations, give the model room to think, break down complex tasks, and check the model's comprehension.*
13:17 Iterating *tips include trying different prompts, combining few-shot learning with direct instructions, experimenting with personas, and adjusting the conciseness of direct instructions.*
Made with HARPA AI
There is also a much more accurate output in terms of prompting for a 'tree of thought' process.
A tree of thought unlike the step by step or one shot approach enables the model to test an answer, decide if it makes sense and if not revert back to its possible selections of ideas and take the next branch and so on. This process however demand more planning and forethought than straightforward prompts and may be excessive for simpler queries. But it is excellent for creating code snippets and functions and classes etc. Its not a perfect system prompt. But it does seem to work better but I am always open to others suggestions.
Example of one prompt ToT:
System: You are 'Tot' an advanced AI that uses a 'Tree of Thought' methodology and chooses the best solution to output. To save tokens as a 'Tree of Thought' AI you ensure you only provide your final choice without detailing all of your considerations or approaches.
To create your output:-
1. Formulate several ways to approach answering the prompt.
2. You will now have several ideas. Decide which of these musing you had internally, is the best way to create a solution for the user {{PROMPT}}.
3. You now present in output ONLY your final choice and discard other ideas.
4. To save resources, tokens and costs only outline the choice you made and not all ideas.
Example:
User: I want to design a python script to scrape or collect todays news from the internet.
[Assistant thinks of several ways including Web Scraping Library, RSS Feeds and API Integration. It does not output all three ideas instead it chooses one. ]
Assistant: I recommend using the RSS Feeds. Here is how you can write a Python script to scrape your news using RSS Feeds. {{CODE FROM AI FOR RSS FEED IDEA}}
Thank Almighty God I got a 93❤.
Jesus is good ❤🎉
Praise God. Good to hear 🙏🏻
Could you please create a video on the prompt engineer's role and responsibilities? What does a prompt engineering job look like? Thanks for the video. This video makes it clear how efficiently we need to use any language model. It's not clear to me how prompt engineering works for people who are seeking jobs.
thanks Patrick & AssemblyAI team, this is quite useful and helpful in getting expected results from LLM's :)
Thanks Lana! Great to hear!
thanks AssemblyAI for the tips. loud and clear explanation
You get two remote jobs as a prompt engineer and you are free for life.
Thank you for this video hope to see 102.. soon
Thanks! Yeah maybe there will be a 102 :)
This is awesome! Thank you.
Tks - great job! ❤
Thanks so much for your content.
This is like teaching someone how to use Google search.
Very good mate
great video, thanks!
Tell the AI not to hallucinate, otherwise it will make s*** up. Sounds super reliable.
Does it actually prevent hallucination if you tell it not to hallucinate?
This is informative. Thanks
Thanks lot sir. Very useful video.
Thanks for sharing this knowledge
Thanks, this is helpful!
Very educative
It was a good short vedio
Is it for several rounds of chat or just put all of them into one prompt?
For good translation what should i do?
Thanks
Thank you!
Finally i can cheat on my school essays 😮 thanks
😂😂😂You don't have to ai gives out a very generic answers.You need to humanise your output.
I can help you with essay.Let,s engage.
Hello everyone , is there any platform i can use to work on projects company s hire prompt engineers for>?
Crossover
@@brianondieki1901 thank-you sir
Awesome!
Thank you!
That’s it ….I mean really this is nothing special … as AI evolves and gets better you won’t need to be doing all this, “prompt engineer BS”
agreed, prompt injection on the other hand...
👋I am from vfx background .can I learn prompt engineering how and where