Annotated History of Modern AI and Deep Learning
A well formatted and concise overview of deep learning from the calculus of 1676, when Gottfried Wilhelm Leibniz please blushed the chain rule to the RL-based NN advancements by DeepSeek in 2025.
The Bernshteyn Bridge and Axiom of Choice
Nice article on the bridge between set theory and computer science (which I’d always thought was there! π) A New Bridge Links the Strange Math of Infinity to Computer Science Also helped remind me what the axiom of choice is; an arbitrary choice that acts as a junction between rule based decisions. I still have to understand the actual algorithm as it seems handy to be able to label infinite nodes so that they do not locally conflict… π€π€
I’ve been digging into paraconsistent and paracomplete logics and hit a useful tangent Foundational Theories and Philosophical Lenses for Maths and Computer Science
Nice to be aware of my bias and the core details of other ways to look at Maths and CS.
Classical Logic versus Paraconsistent Logic
The challenge of contradiction in logic Different starting points of theories that contain contradictions all collapse to the same trivial theory in classical logic. The trivial theory is a bullshit theory that says everything must be true. Trivial is not a term to say it is easy… Rather it’s a term that implies inconsistencies and is pejorative meaning the theory is a mess and useless. Contradiction example The “Penguin Problem”:
The joy of happenstance
Intentions for Math and Philosophy manifest in an unexpected way
Dual state domain
Rough work to be made clearer Domain Table Scope Symbol Name Formal Definition State Space Composite S System State S = S_workflow Γ S_env (Def. 1) Control S_workflow Workflow State {Ο | Ο : G β {β₯, β€}} β truth assignments tracking guard satisfaction Information S_env Environment State π Γ π (Def. 1, Eq. 3) Workflow Components Static G Guard Set {gβ, …, gβ} β unique guard identifiers Dynamic Ο Current State Ο : G β {β₯, β€} β specific truth assignment Function T Transition Function T(s_w, β€) = s_w[g_id β¦ β€]; T(s_w, β₯) = s_w (Def.
Finished reading: Human Compatible by Stuart Russell π
This book is unreal - a must read for anyone interested in AI at a technical level.
I actually finished it about 3 months ago, and have notes all over the place to collate! That is in the maybe one day to do list now… Maybe for a revisit in a year or two.
Finished reading: Dune: The Battle of Corrin by Brian Herbert π
Hmmm…. I listened to it over a few months so I forgot all that happened in this book… Not sure if that’s a reflection of the book or that I’ve been busy…
Still now I have more time I finished the last 25% in 2 days and it was great to see the back story for the Freemen of Arakas and the root of the Artrades/Harkanan rivalry.
Cheesy trope with humans behaving without emotion and robots displaying emotion at the end…. Topical but meh.
The audio book could have been structured better - I’m pretty sure there were more than 2 chapters in the book… I think that made it difficult to parse and remember what was occurring.
F##king did it. π€π
Tomorrow I’ll see if it repeats.
3-4 months of back to basics thinking followed by some surprisingly smooth coding (only one structural update to the formal definitions and a couple of remarks).
Well happy.
Let’s see what tomorrow brings (hopefully it runs again π€πΌ)
Now is π
Be active in your reading
Great video on how to learn: youtu.be/mOJu1I57A… I’m thinking that I - like lots of people - marginalise conversations as well as reading :) Interesting overlap with active listening as well? Need to rewatch to see where this fits in: www.linkedin.com/feed/upda…
I’m trying to think of a song to remember Homotopy - πΆtravelling through a base layer in a Fibrated space and searching for the corresponding path in the fiber! πΆ Don’t stop me now… πΆ π€·πΌββοΈπ€
If any topologists are reading this - Am I correct that the base layer can be discrete?
[IA 10] The case of Claude, the Irrational AI Agent, and the Formal Decomposition of Goals
The discussion explores the challenges and implications of using AI coding agents with “irrational” performance measures, emphasizing the need for explicit goal-based frameworks to improve their functionality and alignment with human intentions.
The need for robots - services and soft skills?
Snippet of a horse article about where we need robots and what skills they will need.
Stephen Wolfram is talking about the Ruliad, Micheal Levin is talking about Platonic Space. They sound very similar… π€
And here’s the language of the space (any space!) π€
Are coding agents offering value?
Positive experience with Claude Code on the web for a small change, will it offer value for bigger changes??
Exciting day today - this quote captures it well.
βThe most important thing in life is to be true to yourself. Because if weβre not true to ourselves, then how can we be true to life?β
Business, innovation, father, husband, son, brother, and friend.
Meditator, artist, and warrior.
Wow π₯³ Awesomely strange when the proofs and lemmas have been written and I'm happy with it!
Wow, I think I’ve just turned the final straight on my paper. It is both, exactly what I thought it’d be and completely new to me. Writing down my intuition, with as much rigour as I can, is a great experience. Now I find out that someone else has already done something similar and I’ve just not understood or found what they have said! Still a great experience to have worked to this point and understand it.
π Explanation of the getKeys Operator
An explanation of the getKeys operator in the Introduction to AI Planning paper from Marco Aiello and Ilche Georgievski (16 Dec 2024).
Degenerate is a tricky term...
The more ways a system can achieve a function, the more robust and adaptable it becomes. I think it is fair to say we tend to think of βdegenerateβ as a pejorative. Something broken, collapsing, or inferior. But in complex systems β biological, neural, or artificial β degeneracy means something far more interesting: different structures performing similar functions.