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

Thank you Andrew Ng for certifying me 🙌

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.

00:01:00 Implement an agentic workflow when working with language models to achieve better results through iterative processes. 00:02:57 Utilize an agentic workflow around language models like GPT 3.5 to outperform traditional zero-shot prompting methods. 00:04:29 Use reflective prompts to improve code quality, such as asking an LM to review its own code for correctness and efficiency. 00:09:29 Experiment with multi-agent systems like ChatGPT to simulate different roles within a software engineering team for complex program generation. 00:11:01 Explore the design patterns of agents, including reflection, planning, multi-agent collaboration, and fast token generation, to enhance productivity in AI applications. 00:11:53 Embrace the concept of patiently waiting for responses from AI agents, even if it takes minutes or hours, to leverage the benefits of agentic workflows. 00:12:51 Focus on generating tokens quickly in agentic workflows to iterate more efficiently, potentially yielding better results than slower token generation from higher-quality models.

Andrew Ng as always great!

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.

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

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

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.

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

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

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

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

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.

Absolutely outstanding talk! Outstanding!

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.

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

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.

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

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."

Great talk! More videos like this please!

I am a big Fan Of Sir Andrew Ng❤

Thanks for sharing!

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

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

great talk!

Really enjoyed this

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

That’s gold!

Great stuff.

The Legend!

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

Great presenatation -)

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

This agentic workflow sounds very much like parsing through iterative phases of collaborative problem solving, that is assumed to be captured in the massive data sets parsed by the networks.

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

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

How do I get started?

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?

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

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

agentic workflows will be come the best way to AGI

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

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

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.

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

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

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

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

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!

10/10

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

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

Andrew should've been mayor :(

"sometimes it works, sometimes it does not"

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

Ng

: whats your real name?

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 :)

I will be happy if I get a B 😂

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

dont uae what you just heard

What a lame introduction!

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.

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.