What's next for AI agentic workflows ft. Andrew Ng of AI Fund

Поділитися
Вставка
  • Опубліковано 25 гру 2024

КОМЕНТАРІ • 149

  • @stephennfernandes
    @stephennfernandes 9 місяців тому +326

    its so soothing to hear andrew ng's voice. brings me back to my coursera ML and DL courses

    • @christopherchen4920
      @christopherchen4920 8 місяців тому +16

      starting from forecasting the house price🤣always in my mind.

    • @Gringohuevon
      @Gringohuevon 8 місяців тому +1

      The misery of Qwiklabs

    • @Taskade
      @Taskade 3 місяці тому +1

      Same, what a great presentation and such an inspiring talk.

  • @waelaburezeq4641
    @waelaburezeq4641 8 місяців тому +13

    The AI legend, I can't forget how easy was learning complext deep learning stuff by just taking Andrew Ng's courses

  • @ReflectionOcean
    @ReflectionOcean 9 місяців тому +23

    00:01:03 AI agents: Iterative, agentic workflows enhance performance.
    00:04:29 Reflective agents: Self-assessment improves code quality iteratively.
    00:09:22 Multi-agent collaboration: Diverse agents boost complex program generation.
    00:12:01 Fast token generation: Rapid token output crucial for iterative workflows.
    00:13:21 AGI journey: Agent workflows propel progress in AI development.

    • @HuxleyCrimson
      @HuxleyCrimson 8 місяців тому +1

      Prompt your AI to be more concise
      They have a tendency for verbosity

  • @TonyKingOfTheOzone
    @TonyKingOfTheOzone 9 місяців тому +107

    I use this method of agentic workflow for coding in school, with brainstorming, and detailed pseudo steps, then review it, then stich somethings together, and have it revise itself. Then after a few cycles, I give it a request using words like "magnificent," or "swe professional point of view," and other things along those lines. Which ends up give me a better product by the final iteration. I am a Sophomore CS student, and I'm glad I am doing the method right, when I'm practicing data structures. Thanks for explaining the method of what I have been doing Andrew Ng.

    • @jatingupta4708
      @jatingupta4708 9 місяців тому +7

      Can u share your workflow

    • @hl236
      @hl236 9 місяців тому +3

      Do you have a blog, youtube channel or x account?

    • @TonyKingOfTheOzone
      @TonyKingOfTheOzone 9 місяців тому

      @@jatingupta4708 I would, but I feel I would need to give like a step process, that would have other bubbles next to bubbles for things to consider. If you give me a few days, Ill give you a generic image generated host paint of my workflow.

    • @TonyKingOfTheOzone
      @TonyKingOfTheOzone 9 місяців тому

      @@hl236 I only use UA-cam and disc for 99% of interactions. I have a git hub with student work I've done, but its nothing special, as its just college freshman and sophomore projects, keep building yall.

    • @enjoful
      @enjoful 8 місяців тому +11

      Excellent humble brag!

  • @pratikkhedikar6759
    @pratikkhedikar6759 9 місяців тому +41

    Hi guys, This is an excellent talk. I watched the Andrej one as well. And it seems that these talks are really focused and talk about real problems. So kudos to the team for executing on this. Its WAY WAY BETTER than these large conference interviews where you don't learn anything

    • @thesadboxman
      @thesadboxman 9 місяців тому +3

      They're also short and straight to the point! This would normally get stretched out to 30m

    • @cesarromerop
      @cesarromerop 9 місяців тому +3

      the anthropic one was not good imo, but the mistral one was good as well

    • @pratikkhedikar6759
      @pratikkhedikar6759 9 місяців тому +1

      @@thesadboxman true

    • @pratikkhedikar6759
      @pratikkhedikar6759 9 місяців тому +1

      @@cesarromerop ohh is it...i didnt checkout the anthropic one....will do

    • @faraimazhandu3806
      @faraimazhandu3806 8 місяців тому +2

      Not limited to this event, I wonder what other talks stand out to you. I am trying to learn as much as I can about this space from experts. Many thanks

  • @ZenBen_the_Elder
    @ZenBen_the_Elder 8 місяців тому +5

    Clip #2 [4:26-6:16]
    I love how Dr Ng humbly describes his work as laying down another brick on the golden road to AGI.

  • @zerobot_tech
    @zerobot_tech 9 місяців тому +17

    Thank you Andrew Ng for certifying me 🙌

  • @reza2kn
    @reza2kn 9 місяців тому +13

    It's nice to see Andrew finally be impressed by something! A lot of his previous talks were along the lines of how AI can't do anything yet and it's not nearly capable, etc.

  • @yashpatel261
    @yashpatel261 9 місяців тому +10

    This is going to change development radically. Imagine being able to just write workflows to write tons of code based on what functionality we want while modulating interconnectedness, dependencies and other finer details and nuances which humans understand and A.I. does not. Just the best of human and ai combining to increase productivity. Excited for the future.

    • @gotoHuman
      @gotoHuman 8 місяців тому +2

      Absolutely. There will always be a human in charge, but insanely more productive. (We are helping LLM devs with that human intervention part)

    • @morespinach9832
      @morespinach9832 7 місяців тому

      Not as easy in enterprises.

  • @matthew_berman
    @matthew_berman 9 місяців тому +48

    Brilliant. The only thing I would add is that with inference speeds offered by Groq, it’s not necessary to wait minutes anymore. Fast inference speeds have the most value when humans aren’t reading the output.

    • @zerobot_tech
      @zerobot_tech 9 місяців тому

      Groq is on ZeroBot if you ever wanna share some thoughts 😉

    • @ravisawhney3111
      @ravisawhney3111 8 місяців тому +2

      Yup, I was wondering what the value is with Groq (like do we really need inference that fast) but agentic worfklows have provided a solid use-case

    • @mayavi93
      @mayavi93 6 місяців тому +1

      Groq is still bad

    • @Ihateteenagerstheyrecringe
      @Ihateteenagerstheyrecringe 6 місяців тому

      ​@@mayavi93 how come? I've never used it

  • @nachoeigu
    @nachoeigu 9 місяців тому +8

    It is always a pleasure to hear Andrew!! :)

  • @1msirius
    @1msirius 8 місяців тому +5

    I'm watching you from age 16, GOAT AI teacher!!!!

  • @Sandheip
    @Sandheip 4 місяці тому

    Insightful discussion on the future of AI agentic workflows with Andrew Ng. Excited to see what innovations are on the horizon. #AIAgenticWorkflows #AI #Innovation

  • @ThinkAI1st
    @ThinkAI1st 9 місяців тому +6

    Agree 100%. To reach AGI/ASI will require agentic workflows.

  • @ayyanarjeyakrishnan6471
    @ayyanarjeyakrishnan6471 8 місяців тому +1

    Great insights as always and I admire AndrewNG explain the advance tech explained in super simple manner !

  • @eado9440
    @eado9440 9 місяців тому +7

    I just did a quick test of this by customizing GPTs how I would like it to respond , its a good fame work , but i dont think its truly agentic .
    "Define the Goal:
    Be specific and measurable. What is the desired outcome of this workflow?
    Identify Key Milestones:
    Break down the overall goal into major checkpoints or phases.
    Flexible Action Steps:
    For each milestone, brainstorm a variety of potential actions that could move you forward.
    Avoid a rigid, sequential task list - these actions are options to choose from.
    Evaluation and Iteration:
    Determine how you'll measure progress towards milestones and the overall goal.
    Build in regular checkpoints for assessment.
    Be prepared to adapt actions, milestones, and even the goal itself based on results.
    Key Principles
    Outcome Focus: Prioritize reaching your goal over following a precise plan.
    Adaptability: Embrace change and be willing to pivot your actions as needed.
    Empowerment: This framework aims to give you agency and decision-making power within the process."

  • @ralfdmueller
    @ralfdmueller 8 місяців тому +5

    Great talk - thanx for sharing!
    Are the slides available for download?

  • @bonadio60
    @bonadio60 9 місяців тому +2

    Andrew Ng as always great!

  • @adtiamzon3663
    @adtiamzon3663 8 місяців тому

    Interesting talk on AI Agent, Andrew Ng. More updates on this subject will help. 🌞👏👏

  • @rommellagera8543
    @rommellagera8543 9 місяців тому +8

    I am 54 this year coding for 3 decades, been using prompt engineering to create my code for last 2 months using multiple GPTs and thought it was the best, but this agentic loop will make programmers legacy, being slow and expensive
    In the next 6 months these workflows will improve, the rise of AI agents will be here whether we like it or not
    I advice knowledge workers to prepare for this financially, physically, mentally and emotionally
    This will be fast, we will be like deer looking at headlights

    • @chillmegachill
      @chillmegachill 8 місяців тому +4

      most knowledge worker are not even aware of AI at all. They will just wake up one day and their job is gone.

    • @Drinksomewatr
      @Drinksomewatr Місяць тому

      no pls..

  • @hl236
    @hl236 9 місяців тому +3

    Fascinating. I'll experiment with agentic workflows for my product. I really like the idea of getting more out of GPT3 using rag and these techniques.

  • @ArthurBerman
    @ArthurBerman 5 місяців тому

    Love learning with Andrew !

  • @danieljbukowski
    @danieljbukowski 9 місяців тому +1

    Absolutely outstanding talk! Outstanding!

  • @TomM-p3o
    @TomM-p3o 9 місяців тому

    Practical overview and feedback of what works and doesn't, very nice

  • @Nifty-Stuff
    @Nifty-Stuff 8 місяців тому +19

    I LOVE AI Agents... but I'm left wondering: Why hasn't anybody developed a system/app that takes the API's from the top LLMs, created agents for each, and then have these agents all work together to brainstorm, debate, review, and solve problems? I often get 4 different answers from 4 LLMs, so why not have them all setup as agents "in one room" working together to come up with the "best" solution. I can't find anybody that's tried this... why not? Wouldn't having the "top minds" (LLMs) working together produce better results?

    • @ThaycMarinho
      @ThaycMarinho 3 місяці тому +1

      I ask myself the same question. I'd like to see real case application bc it seens so unreliable yet

    • @christophscholz7484
      @christophscholz7484 3 місяці тому +1

      do it

    • @ThaycMarinho
      @ThaycMarinho 3 місяці тому

      @@christophscholz7484 already studying and trying

    • @husnainarshed7806
      @husnainarshed7806 3 місяці тому +3

      I think that the only think difficult is to make a good back-end for budget control because it would cost a lot on API and would be unavailable for people that are not willing to pay for this kind of website.

    • @Nifty-Stuff
      @Nifty-Stuff 3 місяці тому

      ​@@husnainarshed7806 that's a really great (and important) point. I think it could be mitigated by: 1) Having the smartest model be the "Manager" of many less-expensive "worker-bee" agents. 2) Setting a "max budget" for the query / project... e.g., "I need this task completed in x days and am willing to allocate $y budget. Do the best you can with the budget / time allocated!" Then the boss agent would be smart enough to budget (time and $$) efficiently. Say it has 10 days... it could use off-peak model times (I assume models will eventually start having time-of-use pricing tiers).

  • @Ikels
    @Ikels 9 місяців тому +1

    Mind-blowing... THANK YOU, Andrew! Great talk.

  • @AudioDestinyHQ
    @AudioDestinyHQ 9 місяців тому +1

    Very nice. Now I want to see how I can use agentic workflows.

  • @philipdante
    @philipdante 9 місяців тому +3

    Great talk! More videos like this please!

  • @Treegrower
    @Treegrower 8 місяців тому +3

    Guys! Make sure to check out the papers he lists at 11:07! It is required reading for the exam 🙂

  • @sandeepvk
    @sandeepvk 8 місяців тому +4

    Love the analogy of the proverbial manager checking every 5 mins after assigning a task 🙃

  • @SandeepMR26
    @SandeepMR26 9 місяців тому +1

    I am a big Fan Of Sir Andrew Ng❤

  • @raymobula
    @raymobula 4 місяці тому

    Very good. I’m currently playing around with the concept of the slow approach.

  • @j0hannes5
    @j0hannes5 8 місяців тому +2

    How do I get started?

  • @DeepCreativeAI
    @DeepCreativeAI 9 місяців тому +10

    great talk!

  • @landob6393
    @landob6393 6 місяців тому +1

    Currently, seems like "AI agents" are just a sequence of LLM requests. Take output and throw it back into LLM, with tools! Conditional loops seems to be the differentiating factor between these chains and real "agents" as I would define them. Any thoughts?

  • @waytolegacy
    @waytolegacy 7 місяців тому +2

    "Maybe you do, I can't do that" 2:39 😆😆

  • @jameehuang
    @jameehuang 3 місяці тому

    The AI's content recommendation engine helps brands discover new trends and topics, ensuring their social media presence remains fresh and relevant.

  • @PlurallyAI
    @PlurallyAI 4 місяці тому +1

    We think that this shift towards agentic workflow will lead to the need of rapidly and consistently train routers to quickly, and smartly route queries to squeeze to most performance of every of the agents.
    This is exactly what we aim to do here at Plurally.
    We are currently in an early access stage, but to anyone looking for such a solution or simply want to try it out - reach out to us (we are very responsive), would love to hear about your specific use cases!

  • @bhaweshs8461
    @bhaweshs8461 6 місяців тому +1

    Andrew is AI legend

  • @zeyuliu4226
    @zeyuliu4226 9 місяців тому +1

    agentic workflows will be come the best way to AGI

  • @nyakarundi
    @nyakarundi 2 місяці тому

    would be curious to get some opinion on running AI agent on the edge without using LLM on premise which we believe is the future.

  • @voranartsirisubsoontorn
    @voranartsirisubsoontorn 9 місяців тому +1

    The world has made AI loud enough but still its directions should be geared to gain the right progress.

  • @elderpinzon7686
    @elderpinzon7686 8 місяців тому +7

    Take a shot every time he says "sometimes it doesn't work, sometimes it's amazing" 😅

  • @micbab-vg2mu
    @micbab-vg2mu 9 місяців тому +2

    Great presenatation -)

  • @paraskevasparaskevas350
    @paraskevasparaskevas350 8 місяців тому +1

    in a way , conceptually, the critic and coder roles are some sort of MoE for LLMs....

  • @marcus-b4x3h
    @marcus-b4x3h 9 місяців тому +3

    3:08 - what's the difference between "Reflection" and "Reflexion"? English is not my first language.

    • @rafaelfigueroa2479
      @rafaelfigueroa2479 9 місяців тому +2

      Reflection is the correct word. Reflexion is a term created by the researchers, with a self-reflection methodology where the LLM reflects on the previous answers to improve it.

    • @marcus-b4x3h
      @marcus-b4x3h 9 місяців тому

      @@rafaelfigueroa2479 merci beaucoup

    • @RR-et6zp
      @RR-et6zp 9 місяців тому +3

      you can also reflect on something. Reflect on the past and reevaluate thighs etc

  • @victorhenriquecollasanta4740
    @victorhenriquecollasanta4740 9 місяців тому +7

    That’s gold!

  • @abcthegreat1
    @abcthegreat1 9 місяців тому +4

    Really enjoyed this

  • @avatarcybertronics2584
    @avatarcybertronics2584 9 місяців тому +1

    The core challenge here is that LLM fails at multi-step planning - and there is no way to guarantee that iterative Reflection bring correct solution (and optimal) in short period of time and money

  • @ashh3051
    @ashh3051 9 місяців тому +3

    To me this approach feels a bit like computer vision before neural networks took over. Hand coding feature detectors etc. That’s what you’re doing when you hand-design a workflow like “do web search, gather sources, write first draft, critique first draft” etc. These hardcoded agent flows are too rigid to produce good results generally. The models will learn to construct their own flows just like a person can. So while people might have some success building agents like this now, I think it’s a bit of a dead end that will be overtaken by foundational models.

    • @hl236
      @hl236 9 місяців тому +2

      Prompt instructions vs zero shot will always be a balancing act that depends on use case. Give too many instructions and you'll nerf the llm. Don't give instructions or use rag and you it will output responses that are low value and not actionable.
      However the value of an llm will always depend on a user's ability to ask the right questions. If Elon musk gave you 30min of his time the value will depends on what you ask him.

    • @whoislewys3546
      @whoislewys3546 9 місяців тому +2

      What he's saying is AI agents of the future will barely resemble the LLMs we have now

    • @gotoHuman
      @gotoHuman 8 місяців тому

      They'll be more autonomous and not just chatbots we can prompt@@whoislewys3546

  • @christiankarren8844
    @christiankarren8844 4 місяці тому

    Great video

  • @steriowang
    @steriowang 5 місяців тому

    Thanks for sharing :)

  • @dadsonworldwide3238
    @dadsonworldwide3238 7 місяців тому +2

    Americans hate to admit it but we've been under such a closed system for so long to the point our public education stopped enriching young minds 40 yrs ago and flipped into recruiting for agency & institutions taking away the most productive years from our workforce.
    It's been 90 years since we was in a very open private sector individual owners and operator creative posture.
    Everyone is a cog in the wheel more or less.
    We have so many grandfathered in economic middle men over the many phases of steam engine until today. Unlike most of the world that only individualized the past 50 years after the transitor age it leaves the west and America with many extra left over obstacles.
    It also leaves debts paid up front that have helped us get to this technology.
    Since I've retired and lived through all that 1900s, structuralism costs classical American decendants its only fair to remind everyone what these are from random Joe's perspective.
    Family birthrates ,18-30 year Olds trained up and entering workforce at the most creative and productive ages ( which by default tends to marry & help Maintain the elusive American prosperity) and the lack or loss of 31 -50 year old owner operators of local American infrastructure.
    Yes it's an unsustainable theme here that's been a very hefty price in building out our world over the 80 years of the transitor age.
    If any sectors are handed advantages in this new paradigm infrastructure, these are the ones who have paid the ultimate cost in my lifetime.
    New paradigm infrastructure where balance is there for better quality of life and at minimum restoration of all that's been compromised.
    We have so antiquated ways of doing things . Our city's are still under top down rule prohibition era reformed control mechanisms

  • @soleverlee317
    @soleverlee317 8 місяців тому +1

    What's the difference between "Agent" and "Agentic workflow"? Will Agent include agentic workflow?

  • @j05hau
    @j05hau 9 місяців тому +1

    Great stuff.

  • @dropacid8
    @dropacid8 9 місяців тому +2

    The Legend!

  • @AdvantestInc
    @AdvantestInc 9 місяців тому +1

    How might agentic workflows transform industries beyond coding, like semiconductors?

    • @laxboi97
      @laxboi97 9 місяців тому +1

      none, other than further increasing the demand for semiconductor products in data centers

    • @whoislewys3546
      @whoislewys3546 9 місяців тому +1

      You could hook up an agent to Verisim and a 3D printer and tell it build better chips for itself

  • @krawlak
    @krawlak 9 місяців тому +2

    Very good talk. I was only distracted by the guy with the restless leg syndrome in the front row. He must have been even more distracting to Andrew, who despite that delivered an awesome talk!

    • @jesussanlv
      @jesussanlv 7 місяців тому

      That’s so funny that you get distracted by the guy. I hadn’t noticed it. Now I will when I re-watch this now lol 😂

  • @vijaykumar-m5p4s
    @vijaykumar-m5p4s 4 місяці тому

    Industries will be transformed by AI agentic workflows. These technologies are now powerful and accessible thanks to SmythOS. #FutureOfWork

  • @balubalaji9956
    @balubalaji9956 9 місяців тому +5

    i thought GPT-3.5 is dumb.
    then Andrew pulled up chart agentic 3.5 beat GPT-4 .

  • @mattkenefick
    @mattkenefick 9 місяців тому +2

    Andrew should've been mayor :(

  • @ramzio9155
    @ramzio9155 8 місяців тому +1

    you want that instant gratif... euuhhh search result :D

  • @angstrom1058
    @angstrom1058 9 місяців тому

    Been doing AI agents operating in async workflows commercially for about 30 years. About time peeps catch up

  • @VPopkins
    @VPopkins 9 місяців тому +1

    "sometimes it works, sometimes it does not"

  • @theAnupamAnandhelueene
    @theAnupamAnandhelueene 9 місяців тому +1

    : whats your real name?

  • @rpbmpn
    @rpbmpn 9 місяців тому +1

    Pretty funny in 2024 how "the cutting edge of computing technology" and "writing scripts for cute AI NPCs" are more or less the same thing :)

  • @elliptictree
    @elliptictree 9 місяців тому +2

    Ng

  • @arthurphiladelpho
    @arthurphiladelpho 9 місяців тому +1

    10/10

  • @TCD企医生
    @TCD企医生 6 місяців тому

    别忘了投资我们

  • @noswag5773
    @noswag5773 8 місяців тому +1

    I will be happy if I get a B 😂

  • @manyes7577
    @manyes7577 8 місяців тому +4

    He still not explain why he gave b to that poor kid

    • @sammyfrancisco9966
      @sammyfrancisco9966 Місяць тому

      He used an agent reflection to give him B. First pass the gent had given the stundent C-

  • @tvm73827
    @tvm73827 9 місяців тому +4

    What a lame introduction!

  • @TulsiKhan-p4c
    @TulsiKhan-p4c 4 місяці тому

    Jai hind

  • @theAnupamAnandhelueene
    @theAnupamAnandhelueene 9 місяців тому +1

    dont uae what you just heard

  • @HideBuz
    @HideBuz 9 місяців тому +3

    This was useless. No real content. Just guesstimations of very vague trends. Just say "Agent Models can wow you, sometimes.", without providing any details or how to build them or what tools to use. - saved your 13 minutes.

  • @jcwfh
    @jcwfh 9 місяців тому +2

    I love Andrew Ng but he has a tendency to speak with an “uptalk” inflection which makes him sound immature and lose his credibility and gravitas. Please Dr. Ng, uptalking is cringey unless you’re an insecure teenager.

    • @benjpac5
      @benjpac5 9 місяців тому +9

      Wait, who sounds like an "insecure teenager"? Yikes

    • @jesussanlv
      @jesussanlv 7 місяців тому

      What is up talking?

  • @Scott-ff2oe
    @Scott-ff2oe 19 днів тому

    Deep.learning

  • @ShivamSharma-ob8ix
    @ShivamSharma-ob8ix 5 місяців тому

    Watching these videos doesn't mean i am joining you! Just for the knowledge sake!