You’ll NEVER Need Prompt Engineering Again with Meta-Prompting

แชร์
ฝัง
  • เผยแพร่เมื่อ 23 พ.ย. 2024

ความคิดเห็น • 103

  • @James-zj9ky
    @James-zj9ky 3 หลายเดือนก่อน +6

    Great job, Mark !!!
    You've explained better than anyone that I've listened to in the past two years how to make A.I. agents do whatever I need them to, and how to fine-tune them to make the results even better.
    I've subscribed and will be listening to your archives as well as waiting for new videos to be posted.

    • @Mark_Kashef
      @Mark_Kashef  3 หลายเดือนก่อน +2

      Thanks for the feedback James! Super appreciate hearing that - will keep trying to pump out value 🦾

  • @thibaultmouillefarine795
    @thibaultmouillefarine795 4 หลายเดือนก่อน +8

    Most comprehensive video on the topic I have seen so far. You are great. Thanks !

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      Means a lot to hear that! Thank you so much 🙏🏻

  • @GabrielRymberg
    @GabrielRymberg 4 หลายเดือนก่อน +5

    I work with Mark on a super exciting project. When I was searching for the right partner, I told myself I want to work with someone who is 10x more knowledgeable than me.
    Mark is it, and much more.

  • @MrShakeelM
    @MrShakeelM 4 หลายเดือนก่อน +6

    Very useful tutorial!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      Great to hear! Thanks for the feedback 🦾

  • @imranfaq
    @imranfaq 2 หลายเดือนก่อน

    Mind Blowing, Excellent.

    • @Mark_Kashef
      @Mark_Kashef  2 หลายเดือนก่อน

      thank you! Much appreciated

  • @ticneslda8929
    @ticneslda8929 4 หลายเดือนก่อน +3

    Great job. Everything was just PERFECT. Keep up the good job!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      Thanks so much! High standard to keep but thanks for the feedback 🦾🙏🏻

    • @charles120001
      @charles120001 4 หลายเดือนก่อน +1

      ​@@Mark_Kashef It's a good video on the intro of Meta Prompting. However, you are assuming the viewer knows as much as you know when you use the words "markdown" and "code block" and what asterisks and hashtags enable you to do or what they are. The majority of the population are new to AI and prompting. I think you need to put yourself in their shoes and ask yourself, will the man on the streets know about "markdown" and "code block" and what asterisks and hashtags are in terms of meta prompting?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      @@charles120001 fair point! thanks for the feedback there Charles, will take it into account.

  • @nicholaskaburia67
    @nicholaskaburia67 4 หลายเดือนก่อน +1

    Great video. Impossible to share how impactful this technique will super charge my business. Thanks 🙏 bro! Yes to more videos like these, cheers

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      Legit so happy to hear that - another one dropping tomorrow on this topic 🤙🏽

  • @yourdailyblockchain
    @yourdailyblockchain 3 หลายเดือนก่อน

    Great vid - appreciate the content - just starting to do some deeper dives into prompt engineering.

    • @Mark_Kashef
      @Mark_Kashef  3 หลายเดือนก่อน

      Thank you! Welcome to the rabbit hole of prompt engineering 😅

  • @iotgen278
    @iotgen278 4 หลายเดือนก่อน +4

    Hey @Mark_Kashef after so many months of looking for the right prompt technique, yours is the BEST!! ever. Thanks for sharing and for making it so easy to understand. I subscribed so I wont miss the part two of this video.

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      So happy to hear!! I’ve got at least two more videos coming out on this 🫡

  • @HenrykAutomation
    @HenrykAutomation 4 หลายเดือนก่อน +3

    Amazing how it went to do the # Role, etc by itself. Amazing, stuff, Poe is a game changer too!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      thanks for the feedback amigo! This is the way of the future haha

  • @breyonbradford3404
    @breyonbradford3404 2 หลายเดือนก่อน

    I have been utilizing this process getting great results and didn’t know this was the official name.

  • @KhalidKafila
    @KhalidKafila 4 หลายเดือนก่อน +1

    This is very helpful Mark.Thank you from Morocco

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      So happy to hear! Thanks for tuning in from Maroc 🇲🇦

  • @Teacher_Curtis
    @Teacher_Curtis 4 หลายเดือนก่อน +3

    Brilliant stuff; many thanks for your excellent professional info... You got a new sub!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      Thank you so much for the feedback, and the sub Curtis!

  • @kadri_akram
    @kadri_akram 2 หลายเดือนก่อน

    Such a great introduction to meta prompting!

    • @Mark_Kashef
      @Mark_Kashef  2 หลายเดือนก่อน

      Great to hear it was helpful!

  • @black_rph
    @black_rph 3 หลายเดือนก่อน +1

    Wooowwwww... A lot of knowledge 💡Thanks for the gems 🙏🏿

    • @Mark_Kashef
      @Mark_Kashef  3 หลายเดือนก่อน +1

      You got it! Thanks so much for the comment 🦾

  • @MH-xx6df
    @MH-xx6df 4 หลายเดือนก่อน +1

    Love your style and approach bro

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      amazing to hear!! thank you so much

  • @shukurabdul7796
    @shukurabdul7796 4 หลายเดือนก่อน +6

    I impreess with how you're explaining as a real genuine teacher. You've got me subscribed . thumbup continue to provide more

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      that means a lot Shukur! I'll keep trying to give that value :)

  • @mikefetherling
    @mikefetherling 4 หลายเดือนก่อน +1

    Great information on prompting Mark - thank you for sharing!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      always a pleasure to see you in the comments haha!

  • @SaminYasar_
    @SaminYasar_ 4 หลายเดือนก่อน +1

    My favorite prompt eng back at it again!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      *lazy prompt eng 🤣🦾

  • @mikew2883
    @mikew2883 4 หลายเดือนก่อน +1

    Very informative tutorial! 👍

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      thanks Mike!

  • @kotizot
    @kotizot 4 หลายเดือนก่อน +2

    greetings from Panama Canal 🙏

  • @muhammadmeer9137
    @muhammadmeer9137 4 หลายเดือนก่อน +1

    Just subscribed pure class

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      Your kind words mean so much - thank you Muhammad! 🦾

  • @uwegenosdude
    @uwegenosdude 4 หลายเดือนก่อน +1

    Hi Mark, next cool video from you which I just found. Thanks a lot.
    Would you recommend to use Poe instead of using a specific Chatbot like ChatGPT or Claude?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      I would only recommend POE if you’re someone like me that wants to test different outputs on a consistent basis.
      The downside of POE is that you don’t have those extra features like Memory, Personal Custom Instructions, etc you have in ChatGPT

  • @scottabergermd
    @scottabergermd 3 หลายเดือนก่อน

    Excellent video and it really gives me a good idea of how to use the AI to generate its own prompts. My question is why do you ask it to output in markdown all the time it just output in regular normal words? Thank you and new subscriber.

    • @Mark_Kashef
      @Mark_Kashef  3 หลายเดือนก่อน +1

      Thanks for the sub Scott!
      Markdown and XML tend to perform better in LLMs as the hashtags and bullets are a proxy for the proxy for importance in the information.
      For example
      # a main header, most import
      ## subheader
      ### sub-title within the airtcle
      ** = bolding
      __ =italics
      basically helps communicate and structure the prompt so that it's easier for the LLM to construe what's the most important from least important

  • @kentondjones
    @kentondjones 4 หลายเดือนก่อน

    This is really great, thanks for the detailed explanation and walk through. One question - what if you wanted to incorporate additional input (upload a text file or paste some data) or some clarifying questions into the prompt? I did try and few different approaches, none with ideal results.

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      My pleasure!
      On the upload front, I’ll usually add a portion where I’ll say ‘hey I’m going to upload this file or paste this data, XYZ is my dream outcome with it, and I need you to push me back with clarifying questions to help me get to said dream outcome with any gaps you’re missing from achieving it’
      {insert example of dream outcome}’
      Something along those lines

  • @indianaellington3323
    @indianaellington3323 3 หลายเดือนก่อน +2

    Prompt Engineering is great, especially when used in seo and other similar areas.

  • @ManjaroBlack
    @ManjaroBlack 4 หลายเดือนก่อน

    This is great. I built a local prompt engineer agent with feedback. Maybe a step up from this?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +3

      Awesome! I just finished a recording a video on how to integrate chain-of-thought into responses to provoke feedback from the user 🦾 it’ll come out next week.

    • @ManjaroBlack
      @ManjaroBlack 4 หลายเดือนก่อน +1

      @@Mark_Kashef nice I’m looking forward to seeing your implementation.

  • @VaibhavShewale
    @VaibhavShewale 4 หลายเดือนก่อน +2

    interesting, i have created something this to create me prompt but it was like back and forth

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      I have a video coming this week with the back and fourth aspect to help fine tune the prompt creation :)

  • @geehammer
    @geehammer 4 หลายเดือนก่อน +1

    Do you have or can you create a video on voice caller prompts please? Outbound/Inbound if possible? PS: You f#cking Rock!

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      One of the next videos I’m releasing is how to apply this technique to building ai agents;
      Taha and I will make a video on voice prompt design 🦾

  • @Dr.SusantaMitra-gx1hy
    @Dr.SusantaMitra-gx1hy 4 หลายเดือนก่อน

    A new direction with nice explanations. The idea will bring a revolutionary change in the traditional concepts of Prompt Engineering. I have already subscribed and liked the video. I also welcome you to my TH-cam channel and hope to get a subscription from such a knowledgeable person like you. Thank you for enlightening us regularly with your promising videos.

  • @mcombatti
    @mcombatti 4 หลายเดือนก่อน +1

    Great video! This is how our prompt generator (Perfect Prompt Creator) and Professor Synapse works 💪 Top prompts and GPTs since Dec 2023 🤗🙌

  • @oreldorf
    @oreldorf 4 หลายเดือนก่อน

    Can you do a video about data analysis using ChatGPT? When I give it a CSV file with campaign data, for example, and ask for insights, it always gives wrong assumptions and creates calculations that are not accurate.

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      Definitely something I can add to my content list!
      In terms of math, chatgpt and LLMs in general lack at calculations since language models don’t excel at maths.
      That’s why chatgpt uses code interpreter, to offload the math to Python to make sure it doesn’t hallucinate.
      I would personally use Claude Projects to due data analysis as it has a lower rate of hallucination that ChatGPT currently.

  • @JarrettJensen-c2q
    @JarrettJensen-c2q 4 หลายเดือนก่อน +1

    Can you provide the prompt that you used?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      Part 1:
      "you are a prompt engineer
      you write very bespoke, detailed, and succinct prompts
      I want you ro write a more better organied and put together prompt of this:"
      ** INSERT PROMPT SAMPLE HERE**
      Part 2:
      "instructions:
      - output the prompt you generate in markdown
      - output the prompt in a codeblock"

  • @iangordon1
    @iangordon1 4 หลายเดือนก่อน +1

    🔥🔥🔥🔥

  • @thays182
    @thays182 4 หลายเดือนก่อน +1

    Subbed

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      appreciate you!

  • @easypeasy2938
    @easypeasy2938 4 หลายเดือนก่อน

    Great content. Just found you, you got my subscribe. Question: I am new to all this. I need to do some large scale research (over 8000 entries) where the information is not aggregated anywhere. The only solution I can see is to call each contact and ask for the relevant information. (i need to get the name and email of the executive directors of all senior communities east of the Mississippi with resident populations over 50.) Any ideas?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +3

      thanks so much! means a lot and appreciate your sub
      In terms of your task, there's multiple ways to slice it.
      Route 1 (manual) - you hire a virtual assistant offshore to go through LinkedIn profiles and/or search online directories to identify senior communities and log all this information for you in a Google Sheet.
      Route 2 (semi automated) - using an intelligence tool like ZoomInfo or ClearBit which pretty much sell you access to many leads work information.
      Route 3 (automated) - using something like MeetAlfred to automatically target or reach out to individuals in your target market:
      meetalfred.com/articles/at-ulink-linkedin-automation
      Best ways that come to mind. Hope that helps!

    • @thibaultmouillefarine795
      @thibaultmouillefarine795 4 หลายเดือนก่อน

      Hello. The answer is a workflow with make

    • @easypeasy2938
      @easypeasy2938 4 หลายเดือนก่อน

      @@thibaultmouillefarine795 could you be more specific?

  • @SMCGPRA
    @SMCGPRA 4 หลายเดือนก่อน +1

    Why can't LLM model have generic templates?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      do you mean templates embedded within the training itself? I would imagine they’d rather not constrain the model and put it in a box that’s stuck to a few templates.

  • @drn1designer908
    @drn1designer908 3 หลายเดือนก่อน

    parabens -ptbr

  • @hauslab8479
    @hauslab8479 4 หลายเดือนก่อน +1

    May I see a chat gpt bot built for you in open AI store?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      I don't have any actively in the store at the moment, all just personal or shared.

  • @themax2go
    @themax2go 4 หลายเดือนก่อน +2

    seo-optimized... so it's double-optimized?? 🧐🤔

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      meta optimized 🤓

  • @kotizot
    @kotizot 4 หลายเดือนก่อน

    I do really love legit people like you, Mark God Bless You for been an ORIGINAL, Knowledge Giver !

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      Thank you so much!! Means a lot to hear, will keep aiming to provide more value 🚀

    • @kotizot
      @kotizot 4 หลายเดือนก่อน

      @@Mark_Kashef 👌🤘

  • @bunnystrasse
    @bunnystrasse 4 หลายเดือนก่อน

    Mark Kashef, what is your Fiverr profile?

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      It's here!
      Link: www.fiverr.com/datascience2go

  • @lightloopfactsideas5770
    @lightloopfactsideas5770 หลายเดือนก่อน

    Please correct your video timestamps

    • @Mark_Kashef
      @Mark_Kashef  หลายเดือนก่อน

      noted with thanks

  • @magicismagic123
    @magicismagic123 4 หลายเดือนก่อน

    just use claude prompt generator and all solved

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      For Claude prompts maybe 🤔
      Llama 3 prompting will look vastly different; this also removes all dependence on these tools and puts it on the LLM themselves

  • @pliniocastro1546
    @pliniocastro1546 3 หลายเดือนก่อน

    The idea is somewhat interesting but not scientific as spected judging by the self professional description nor is groundbreaking as the clickbait suggests.
    An idea to have something closer to mathematicaly tested prompting would be generating the instruction in json format and the instructions in xml structure

    • @Mark_Kashef
      @Mark_Kashef  3 หลายเดือนก่อน

      thanks for the feedback

  • @hitmusicworldwide
    @hitmusicworldwide 4 หลายเดือนก่อน +7

    You are not being economic with input tokens " I want you to write " is not necessary. a simple directive is all that is necessary. "Write ...." Conversational colloquial English is superfluous . It's a vector database so break up long sentences into short , direct, active voice instructions. Surely your research has taught you that . The responses should also be directed to be economical in output tokens spent unless otherwise directed .

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +2

      thanks for your feedback - this video is meant to focus on the 'how' to use the technique rather than how to optimize the use of this technique in LLM production-based applications. If you're using a front-end with a no limit on token usage, being superflous with wording isn't a consideration

    • @hitmusicworldwide
      @hitmusicworldwide 4 หลายเดือนก่อน

      @@Mark_Kashef economy in programming and clear, concise thinking is never optional when it comes to constructing logic which is what we are doing. This very much is part of the "how" to use efficiently. There is always a cost when we are not efficient and economical

    • @1lostplatoon
      @1lostplatoon 3 หลายเดือนก่อน +2

      @@hitmusicworldwidethere’s more than one way to do one thing though chill

    • @jpheeter
      @jpheeter 3 หลายเดือนก่อน +1

      I think the consideration of prompt engineering as an extension of the way we speak rather than the way we code should be taken into account. as the models become more proficient with the nuances of language our superfluous speech patterns will become the norm just as with a standard human-human conversation.
      That's not saying communicating in a code style isn't efficient now, just something I think future us will be leaving behind as the technology evolves.

    • @Mark_Kashef
      @Mark_Kashef  3 หลายเดือนก่อน +1

      @@jpheeter completely agree, love this perspective! Appreciate you chiming in.

  • @jasonreviews
    @jasonreviews 4 หลายเดือนก่อน

    then hak tua chick does a video obliterates the rest of us going viral. I really question reality. it's mostly dumb luck at this point for everything

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน

      hopefully this video is more valuable than that 🤣

  • @abboudkarim
    @abboudkarim 4 หลายเดือนก่อน +1

    I heard that the output in these bots are limited when compared to it`s navite platforms

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      The front-end ChatGPT and Claude AI have an internal system prompt that alters the LLM’s behaviour!

    • @abboudkarim
      @abboudkarim 4 หลายเดือนก่อน +1

      @@Mark_Kashef I mean on Poe, output tokens are diminished

    • @Mark_Kashef
      @Mark_Kashef  4 หลายเดือนก่อน +1

      @@abboudkarim if it's a very long output, yes, but they just released an artefacts feature like Claude to get around that