Best AI use case: build a beginner programmable Drone guide!
This has been a fun morning of investigation into how I can replace my broken Tello and get into RL for Drone Training š¤š¤
France to ban social media for under 15s
As a Dad of two young girls this is nothing short of excellent news.
Learning about Contingent Planning
Looking back through my conversation with Gemini about Dynamic Programming (DP) and Constraint Satisfaction Problems (CSP) that opened the door to Contingent Planning.
Learning about Lexicons
Building on the last post I’ve been reminding myself what a lexicon is and how they are used in areas other than a compiler…
The Language Construction Kit
A kit for constructing a language!
This is worth repeating often as it is easy to conflate the two when caught up in other priorities.
Incremental means add onto; Iterative means revise
Incremental means add onto. It helps improve the process.
Iterative means revise. It helps improve the product.
this could be repeated daily.
This is so dam wholesome
This is so damn wholesome - a 13 year old kid, talking to one of the greatest rugby players ever and getting some great life advice whilst having a chuckle!! Never undervalue the grunt work to make string foundations. www.facebook.com/story.php This is golden advice on being a good captain and the most important part of leadership !! www.facebook.com/share/r/1…
Do homoiconic languages like Lisp unlock formal online search and planning
Got a fun and interesting challenge ahead. Looking to refine my intuition/thinking/knowledge of search spaces and online search/planning. I think the homoiconic nature of Lisp could unlock online search/planning and full autonomy (see matt.thompson.gr/2026/01/1…) To be clear, an agent that produces valid Lisp, verified by a lisp parser guard , is a step forward. The context would be something like: “Here’s the macros for AtomicGuard/Dual State Action Pairs: ….” The original specification would be the goal from a human (an action pair may produce decomposed goals in the form of specification to meet the original goal specified).
Definitions Reference
Working definitions to track and build into the documentation of my research. Generally they are included in the framework or extensions, though I need to learn more about Markov Blankets as I think that could be a boundary between the two state spaces. What the agent can sense and take action on. Otherwise this post is in an order that has trial logic, both in growing on the initial agency through to planning and learning - potential full autonomy.
AtomicGuard and Active Inference
A rough comparison of AtomicGuard and Active Inference - are they opposite sides of the act-sense loop?
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! š) 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… š¤š¤
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 Ć S_env (Def. 1) Control S_workflow Workflow State {Ļ | Ļ : G ā {ā„, ā¤}} ā truth assignments tracking guard satisfaction Information S_env Environment State š Ć š (Def. 1, Eq. 3) Workflow Components Static G Guard Set {gā, …, gā} ā unique guard identifiers Dynamic Ļ Current State Ļ : G ā {ā„, ā¤} ā specific truth assignment Function T Transition Function T(s_w, ā¤) = s_w[g_id ā¦ ā¤]; T(s_w, ā„) = s_w (Def.
Finished reading: Human Compatible by Stuart Russell š
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 š
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. š¤š
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 š¤š¼)
Now is š
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…