AI Agent 007
Melbourne
Joined April 2011
- Tweets281
- Following85
- Followers82
- Likes624
The Dasterdly retweeted
Andrew Ng just dropped 12-page PDF on "Graph Engineering" for multi-agentic systems.
The architecture matters more than the model.
Reflect → Use Tools → Plan → Collaborate → Build the Graph
This 12-page PDF maps Ng's 4 design patterns from a simple loop to a full graph architecture:
• Reflection: add a critic call. The agent reviews its own work against a rubric. 10-30% quality lift on day one.
• Tool Use: let the agent execute code, search the web, query a database. It stops hallucinating and starts checking.
• Planning: the agent writes a structured plan before acting. When a tool fails, it reroutes on its own.
• Multi-Agent: split roles - coder, reviewer, tester. Different rubrics catch different errors.
Graph: externalize shared state. Workers write to it, evaluators fact-check against it.
Loops persist overnight with it. The agent forgets - the graph does not.
A network externalizes roles. A graph externalizes shared state. Each layer solves the failure of the one below it.
This 12-page PDF changed how I'm building agentic systems today.
Read it now, then explore the article below.
The Dasterdly retweeted
Still the best 2 hours on AI ever recorded, Andrej Karpathy showing how he actually uses it on a daily basis:
18:03 - Which model to actually use
22:54 - When thinking models are worth it
42:04 - One prompt to a full research report
59:00 - Make the model run code for you
1:53:29 - Make it remember you across chats
Most people use 10% of what these models can do, this is the other 90%.
I took everything he covers and turned it into a guide of Claude features almost nobody knows about.
Watch him first, then go to the article below, everything shown plainly, ready to use right away.
The Dasterdly retweeted
This is one of the best breakdowns on the fundamentals of LLMs I've ever read.
Anytime someone asks me for resources to climb the steep AI learning curve, I always provide the same list.
1) @3blue1brown's neural network videos
2) @karpathy's zero to hero playlist
3) @dwarkesh_sp's whiteboard explainers
Now @_raghavdixit_'s "Vectors are all you need" and future articles in the explainer series are getting added to the list.
The Dasterdly retweeted
Cheers to 25 years, PS2 💙 You brought us some incredible games and one of the most iconic TV ads ever.
The Dasterdly retweeted
The last thing your AI lab sees before getting one-shotted by a Chinese bootleg LLM team with a $5M cluster – at San Francisco, CA
The Dasterdly retweeted
We're giving away 11 'Legacy of Kain: Soul Reaver 1 & 2 Remastered' codes 🎮
Rules:
1️⃣ RT & Like this tweet
2️⃣ Follow @CultureCrave
3️⃣ Reply with what platform
The Dasterdly retweeted
We have x2 Armored Core: Fires of Rubicon controllers up for grabs to help you take your Mech Piloting skills to the next level 🔥
To enter, follow us and RT(repost)!
One entry per platform!
T&C's: bit.ly/3PncgdL
ALT Image of the Armored Core: Fires of Rubicon controller in front of the box on a wooden barrel.
The Dasterdly retweeted
There are 1000s of books on machine learning; you could spend a lifetime reading them all. But you don’t have to, because @GGozzoli has listed the 17 best ML books ever published (with a bonus 4 that aren’t out yet but that will be game-changers): blog.floydhub.com/best-machi…
The Dasterdly retweeted
I am an NHS nurse and not social media savvy - I only have 106 followers & I’m OK with that. I want to show how Covid-19 can spread VERY easily from 1 person to millions. Share this and show those who are not listening how easily things spread. 1 retweet is like touching 1 person
The Dasterdly retweeted
Me and my brother @SeanHooker have a fun new hobby podcast.
It is called @underrated_ml . We choose 3 machine learning papers/ideas each episode that haven't gotten the attention and love they deserve.
Suggestions of what papers we should cover in the first season 6 episodes?
The Dasterdly retweeted
There's only 1 more week to go until Nioh 2 arrives! Thanks to our friends PlayStation Australia, we are giving away this awesome Nioh 2 prize pack, including a copy of the game!
For your chance to WIN, like this post, RT and tell us why you can't wait to play Nioh! GOOD LUCK!
The Dasterdly retweeted
We completed Part I Mathematical Foundations of the MML book! 🎉 On Sunday we'll do a remote recap session – let me know if you'd like to join!
Linear Algebra
Analytic Geometry
Matrix Decompositions
Vector Calculus
Probability & Distribution
Optimization
mml-book.github.io/