Anthropic's Meta Prompt: A Must-try!

แชร์
ฝัง
  • เผยแพร่เมื่อ 19 ม.ค. 2025

ความคิดเห็น • 118

  • @icandreamstream
    @icandreamstream 10 หลายเดือนก่อน +15

    Perfect timing, I was experimenting with this myself yesterday. But this is a much more in depth take, I’ll have to check it out.

  • @IvarDaigon
    @IvarDaigon 10 หลายเดือนก่อน +22

    I guess one use case might be using a larger LLM to create system prompts for a smaller faster model to enable it to better follow instructions and collect information before the information is summarized and then passed back to the larger model to formalize.
    For example. Model A instructs model B how to interview the customer and collect the required information which then gets passed back to model A to fill out and submit an online form.
    this approach would be faster and cheaper than getting model A to do all of the work because A-teir models are often 10X the cost of B-tier models.
    This kind of system would work really well when collecting information via email, instant message or over the phone.

    • @keithprice3369
      @keithprice3369 10 หลายเดือนก่อน

      Interesting. I was envisioning the opposite. Use Haiku to generate the prompt and pass that to either Sonnet or Opus. Worth experimenting with both, I think.

    • @davidw8668
      @davidw8668 10 หลายเดือนก่อน +1

      DSPy pipeline work indeed kinda that way, so you use larger models in the beginning to optimize prompts and finetune automatically, create data with larger models to train smaller models, and then run the decomposed tasks on smaller models and evaluate the pipeline using larger models

  • @erniea5843
    @erniea5843 10 หลายเดือนก่อน +4

    Appreciate you bringing attention to this. Great walkthrough

  • @CYBERPOX
    @CYBERPOX 10 หลายเดือนก่อน +1

    This is the truth. It is just semantically and Syntactically difficult to adjust to them all. If you add the video, and audio generation it gets 😅 great video!

  • @MattJonesYT
    @MattJonesYT 10 หลายเดือนก่อน +3

    Whenever I do A/B testing between chatgpt and the free claude model I end up choosing chatgpt mainly because for whatever reason claude tends to hallucinate in authoritative sounding ways whereas if chatgpt doesn't understand something it is more likely to admit that (but not always). For instance today I told claude I added PEA to a gas engine and it assumed I was using biodiesel and proceeded to give a long chat about that. Chatgpt understood that PEA is polyetheramine for cleaning gas systems. So it's hard for me to take claude seriously as yet.

  • @Taskade
    @Taskade 10 หลายเดือนก่อน +4

    Thanks for sharing this insightful video! It's great to see how Anthropic's Metaprompt can really enhance prompt quality and model interactions. Looking forward to experimenting with it myself. Keep up the awesome work! 😊👍

    • @levi2408
      @levi2408 9 หลายเดือนก่อน +1

      This comment has to be AI generated

    • @MartinBroadhurst
      @MartinBroadhurst 9 หลายเดือนก่อน

      ​@levi2408 thanks for sharing your interesting insights into fake AI generated comments. I can't wait to learn more about AI generated spam.
      😉

  • @proflead
    @proflead 5 หลายเดือนก่อน

    Great walkthrough! Thanks Sam!

  •  9 หลายเดือนก่อน

    Really interesting. This will help having hyperspecialized agents. When we know that swarms of these are the future of AI, at least for the coming month ... Thank You Sam

  • @WhySoBroke
    @WhySoBroke 10 หลายเดือนก่อน +2

    Great tutorial and nicely explained. I believe you assume a certain level of knowledge from the viewer. For a beginner where do we enter the Claude api key? Just as an example of things you assume the viewer already knows. Maybe direct to a basic video explaining so it is not redundant?

  • @aleksh6329
    @aleksh6329 10 หลายเดือนก่อน +2

    There is also a framework called DSPy by Omar Khattab that attempts to remove prompt engineering and it works with any LLM!

  • @alextrebek5237
    @alextrebek5237 10 หลายเดือนก่อน +7

    Criminally underrated channel

  • @Stewz66
    @Stewz66 10 หลายเดือนก่อน +7

    Very helpful, constructive, and practical information. Thank you!

  • @QueenLover-j5i
    @QueenLover-j5i 9 หลายเดือนก่อน

    By YouSum
    00:01:58 Utilize Metaprompt for precise AI instructions.
    00:08:49 Metaprompt aids in generating detailed and specific prompts.
    00:10:42 Metaprompt ensures polite, professional, and customized AI responses.
    00:11:55 Experiment with Metaprompt for tailored AI agent interactions.
    By YouSum

  • @polysopher
    @polysopher 10 หลายเดือนก่อน +2

    Totally what I think the future will be!

  • @TheRealHassan789
    @TheRealHassan789 10 หลายเดือนก่อน +4

    Idea: use RAG to grab the closest prompts from GitHub repos to inject into the meta prompt notebook…. This would probably give even better results?

    • @samwitteveenai
      @samwitteveenai  10 หลายเดือนก่อน +3

      there are some really nice research and applications of using RAG to choose the best exemplars/examples for few shot learning. What you are saying certainly makes sense.

  • @odw32
    @odw32 10 หลายเดือนก่อน

    Looking at how we work together with humans, it would make a lot more sense if the prompting process could be split up: First you chat/onboard the model with the right task/context, they ask for clarifications where needed, then they execute a task, and ask for a review/feedback reflecting back on what they did.
    Especially the "ask for clarification", "admit lack of knowledge" and "request feedback" parts aren't a default part of the commercial tools yet.
    Luckily things like meta-prompting and using LangChain agents all seem to converge in that a direction though, like little pieces of the puzzle.

  • @oruzlorte1691
    @oruzlorte1691 7 หลายเดือนก่อน

    Hi Sam. THX, I am a newbee. I don´t understand why I have to use google Colab?. Is there a difference if i use the AI Anthropic Opus directly? The Output is the same or not? I wil get the prompt with variables in google colab or direct in A. Opus.

    • @samwitteveenai
      @samwitteveenai  6 หลายเดือนก่อน

      you can use it directly as long as you copy the prompt over fully etc. Colab is showing how to do it through the API

    • @oruzlorte1691
      @oruzlorte1691 6 หลายเดือนก่อน

      @@samwitteveenai o direct would be the similar output. Except that it's free.
      Because via Colab I would have to pay for the API. Did I understand correctly?

  • @LucianThorr
    @LucianThorr 9 หลายเดือนก่อน

    What is the "typical" UX for developers who are using these LLVMs on a daily basis? Is it all in Notebooks like the above video? Web browser based conversations? IDE integrations? And especially if IDE, how do you keep your proprietary code from being scanned and leaking back up to these companies?

  • @AnimusOG
    @AnimusOG 10 หลายเดือนก่อน

    My favorite AI Guy, thanks again for your content bro. I hope I get to meet you one day.

  • @damien2198
    @damien2198 10 หลายเดือนก่อน +1

    I use a GPT Claude 3 prompt Optimizer (it loads Claude prompt documentation / cookbook into chatgpt)

  • @ShawnThuris
    @ShawnThuris 10 หลายเดือนก่อน

    Very interesting, there must be so many use cases for this. (Minor point: in August the time is PDT rather than PST.)

  • @alchemication
    @alchemication 10 หลายเดือนก่อน +1

    Interesting, just when I concluded that too long prompts are not good and usually a symptom of trying to cram in too much info ;D (depending on the situation obviously). Nevertheless the concept is nice, and indeed some of us utilised it for a long time for prompt development and optimisation ;)

  • @matthewtschetter1953
    @matthewtschetter1953 10 หลายเดือนก่อน

    Sam, helpful as always, thank you! How do you think these promopting cookbooks could help agents perform tasks?

  • @fburton8
    @fburton8 10 หลายเดือนก่อน

    Probably a silly question, but why is the "and" at 4:24 blue?

    • @einmalderfelixbitte
      @einmalderfelixbitte 9 หลายเดือนก่อน

      I am sure that is because ‘and’ is normally used as an operator in boolean equations (like ‘or’). So the editor (wrongly) highlights it everywhere even when it is not used as a logical operator.

  • @ronnieleon7857
    @ronnieleon7857 10 หลายเดือนก่อน

    Hello Sam. I hope you're holding up well. There's a video you talked about open-sourcing a web scraping tool. Did you open-source the project? I'd like to contribute to a tool that automates web scraping.

  • @joser100
    @joser100 10 หลายเดือนก่อน

    This looks great but very specific to Anthropic models, no? is not that what we are after with using programmatic tools such as DSPy for example to reach the same goal but more "generically"? (similar with Instructor only that this one more focused on formatting I think)

  • @manikyaaditya1216
    @manikyaaditya1216 9 หลายเดือนก่อน

    hey this is insightful, thanks for sharing it. The colab link seems to be broken, can you please share the updated one.

  • @mushinart
    @mushinart 10 หลายเดือนก่อน

    cool video ,sir ... did langchain optimize it for claude 3 yet ?

    • @samwitteveenai
      @samwitteveenai  10 หลายเดือนก่อน

      Yeah you can use LangChain with Claude 3 no problems

  • @benjaminanderson1014
    @benjaminanderson1014 9 หลายเดือนก่อน +2

    So we've successfully outsourced ai prompt engineering to ai? Cool.

    • @samwitteveenai
      @samwitteveenai  9 หลายเดือนก่อน

      For some things. It certainly helps.

  • @jarosawburyk893
    @jarosawburyk893 10 หลายเดือนก่อน

    I wonder how Claude specific it is - would it generate good prompts for OpenAI GTP4 ?

    • @samwitteveenai
      @samwitteveenai  10 หลายเดือนก่อน +1

      Certainly worth a try. You can alter it and also run on OpenAI or Gemini etc as well

  • @micbab-vg2mu
    @micbab-vg2mu 10 หลายเดือนก่อน

    At the moment I use personalise prompts for every task diffrent one - the quality output is much higher:)

  • @gvi341984
    @gvi341984 9 หลายเดือนก่อน

    Claude free mode only lasts a few messages until pay wall

  • @mikeplockhart
    @mikeplockhart 10 หลายเดือนก่อน

    Thanks for the content. With meta prompting in mind, do you thing something like DSPy is a more programmatic alternative or there doing similar things under the hood? And if you’re looking for video ideas… 😊

    • @samwitteveenai
      @samwitteveenai  10 หลายเดือนก่อน +1

      have been playing with DSPy a fair bit with some interesting results. It is quite a bit different than Metaprompt but has some very interesting ideas.

  • @armankarambakhsh4456
    @armankarambakhsh4456 10 หลายเดือนก่อน

    Wont the metaprompt work if I just copy it into claude main interface itself?

    • @samwitteveenai
      @samwitteveenai  10 หลายเดือนก่อน

      yesyou can certainly do something similar like that

  • @mikeyai9227
    @mikeyai9227 9 หลายเดือนก่อน

    What happens when your output has xml in it?

    • @samwitteveenai
      @samwitteveenai  9 หลายเดือนก่อน

      You can parse it very easily.

  • @KeiS14
    @KeiS14 10 หลายเดือนก่อน

    This is cool and all but what is 4? 1:03

  • @harigovind511
    @harigovind511 10 หลายเดือนก่อน +1

    I am part of a team who is building a GenAI powered analytic tool, we still use a combination of GPT-3.5 and 4…Don’t get me wrong Claude is good, specially sonet the price to performance ration is just out of this world, I guess we are just primarily impressed by OpenAI’s track record of releasing quality model which are significantly better than the previous version under the same API umbrella.

  • @TheBlackClockOfTime
    @TheBlackClockOfTime 10 หลายเดือนก่อน

    I thought my screen was scratched there for a second until I realized it's the human head logo's grey outlines.

  • @nicdemai
    @nicdemai 10 หลายเดือนก่อน

    The meta prompt is a feature currently in Gemini Advanced but its not released yet. Although it’s not as detailed as this.

    • @Walczyk
      @Walczyk 10 หลายเดือนก่อน

      you mean how it writes out a list first?

    • @nicdemai
      @nicdemai 9 หลายเดือนก่อน

      @@Walczyk No i mean when you write a prompt. Before you send it to the Ultra model another model tried to modify it to make it longer and more detailed with concise instructions before sending it to the Ultra model.

    • @Walczyk
      @Walczyk 9 หลายเดือนก่อน

      oic, i had a feeling it was doing that; because it would read out this clean structure of what it would do; i could see it had received that as its prompt@@nicdemai

  • @codelucky
    @codelucky 10 หลายเดือนก่อน

    Thank you, Sam. I'm excited to dive deep into Metaprompt and learn how to create comprehensive prompts with precise instructions that produce the desired outcomes for users. Can you suggest a course or resource to help me get started on this journey?

  • @Koryogden
    @Koryogden 10 หลายเดือนก่อน

    META-PROMPTING!!!! YES!!!! This topic excites me!

  • @LaHoraMaker
    @LaHoraMaker 10 หลายเดือนก่อน +1

    Maybe this is the work of the famous Prompt Engineer & Librarian position at Anthropic with a base salary of 250-375k USD :D

  • @heresmypersonalopinion
    @heresmypersonalopinion 10 หลายเดือนก่อน +1

    I hate it when it tells me " i feel uncomfortable completing this task".

  • @SonGoku-pc7jl
    @SonGoku-pc7jl 8 หลายเดือนก่อน

    cool! :) thanks!

  • @ivancartago7944
    @ivancartago7944 10 หลายเดือนก่อน

    This is awesome

  • @AntonioVergine
    @AntonioVergine 10 หลายเดือนก่อน

    Am i the only one thinking that if i have to "fix my prompt or the AI won't understand" it means that the AI simply is not good enough yet?

    • @samwitteveenai
      @samwitteveenai  10 หลายเดือนก่อน +1

      Kinda yes, kinda no. You could imagine you have to talk to different humans in different ways etc. Models are like. Of course ideally we would like them to understand everything we want, even humans aren't good at that though

  • @GeppettosAi
    @GeppettosAi 10 หลายเดือนก่อน +1

    Metaprompt feeling like a RAG of all models.

  • @hosst
    @hosst 10 หลายเดือนก่อน

    wonderful

  • @amandamate9117
    @amandamate9117 10 หลายเดือนก่อน

    i love this

  • @JC-jz6rx
    @JC-jz6rx 9 หลายเดือนก่อน

    Problem is cost. Imagine sending that prompt on every API call

    • @samwitteveenai
      @samwitteveenai  9 หลายเดือนก่อน

      you don't need to send this prompt each time. the idea is this makes a prompt that is much shorter that you can use.

  • @ellielikesmath
    @ellielikesmath 10 หลายเดือนก่อน

    prompt engineering still seems like a such dead end. if it requires each prompt be unrolled into something with a lot of common sense filler, why not add that as a filter to the LLM? so you feed in your prompt, some automated system makes reasonable guesses as to what filler to pack it with, and then see what the LLM makes of it. the problem is the user thinks all of the assumptions they make are obvious and shared by the LLM, and it's not always the case. I'd be interested to know if any LLM tries to predict sentences/clauses the user left out of their prompt, or heaven forbid, ask the user questions!! about what they may have omitted or meant. this is but one way out of this nonsense, and i assume people are trying lots of ways to get rid of this besides what i am suggesting.

    • @Koryogden
      @Koryogden 10 หลายเดือนก่อน

      What I was trying myself, is a Style/Principles Guide Framework... It just doesn't quite apply the principles though, but it did qualitatively increase responses

  • @JaredFarrer
    @JaredFarrer 9 หลายเดือนก่อน

    Yeah but nobody wants to try and figure out how to word things so the model will respond it’s junk. I wouldn’t pay for Gemini

  • @sbutler860
    @sbutler860 10 หลายเดือนก่อน

    I asked Claude 3 questions: 1. Who won the FA Cup in 1955? 2. Which composer won the Academy Award in 1944 and for which film? What was the date of the death of Queen Elizabeth II? CLAUDE got all three questions WRONG. I asked the same of Google's Gemini and it got all three CORRECT. I also asked the same questions of Windows' CO-PILOT, and it also got all three correct, although it took its sweet time about it. Therefore, Claude may know how to metaprompt a travel agent, but it doesn't know its arse from its elbow about anything else. Long live Google Gemini! And Co-Pilot! x

  • @llliiillliiilll404
    @llliiillliiilll404 9 หลายเดือนก่อน

    00:00:35 - watching this guy typing with two fingers is so painful

  • @xitcix8360
    @xitcix8360 10 หลายเดือนก่อน

    I want cook the soup

  • @TheMadridfan1
    @TheMadridfan1 10 หลายเดือนก่อน +33

    Sadly OpenAI is acting worthless lately. I sure hope they release 5 soon

    • @nickdisney3D
      @nickdisney3D 10 หลายเดือนก่อน +19

      After using claude, gpt4 is poop.

    • @tomwojcik7896
      @tomwojcik7896 10 หลายเดือนก่อน +6

      @@nickdisney3D really? in what areas did you find Claude (Opus, i assume) significantly better?

    • @rcingfever3882
      @rcingfever3882 10 หลายเดือนก่อน +8

      I would say in conversation for example if you see a diference in gpt 3.5 and gpt 4 the later just understands better. Same is true between gpt 4 and opus not a lot but slightly. And when it comes to coding and image generation to make a small change on my website i had to prompt i guess 10 times to make understand when it comes to gpt4 but for opus i got it in first time.

    • @rcingfever3882
      @rcingfever3882 10 หลายเดือนก่อน

      .​@@tomwojcik7896

    • @nickdisney3D
      @nickdisney3D 10 หลายเดือนก่อน +3

      @@tomwojcik7896 everything. Except that it gets emotional and moody when you push it the right way. I had a chat with it today where it just refused to respond.

  • @motbus3
    @motbus3 10 หลายเดือนก่อน

    It is ridiculous that each AI model should be prompted in a different way.

  • @JaredFarrer
    @JaredFarrer 9 หลายเดือนก่อน

    OpenAI has really dropped the ball lately bad leadership

  • @exmodule6323
    @exmodule6323 10 หลายเดือนก่อน +6

    Tighten up your delivery man, I had to stop listening because your intro was too long

    • @roc1761
      @roc1761 10 หลายเดือนก่อน +3

      Can't you take what you're given...

    • @cas54926
      @cas54926 10 หลายเดือนก่อน +3

      Someone might have attention span issues 😂

    • @Koryogden
      @Koryogden 10 หลายเดือนก่อน +2

      ????? What????

    • @bomarni
      @bomarni 10 หลายเดือนก่อน

      1.75x speed is your friend

    • @ronaldokun
      @ronaldokun 9 หลายเดือนก่อน +1

      Be cool, man. Someone is teaching you something. You can increase the speed and give a nice feedback. Everybody wins.