Matthew Thompson

How do we Plan? First we Sense. How do we Sense? First we Plan the Sensing argh.: https://matt.thompson.gr/2026/02/18/how-do-we-plan-first.html

It’s a trap!

Research Links Collection for Reasoning (LLM and other types): https://matt.thompson.gr/2026/02/18/research-links-collection-for-reasoning.html

Links I collected last summer on Reasoning - large amount LLM links but it goes past that into what is reasoning and the cognitive link (I went too far ...

Best AI use case: build a beginner programmable Drone guide!: https://matt.thompson.gr/2026/02/01/best-ai-use-case-build.html

This has been a fun morning of investigation into how I can replace my broken Tello and get into RL for Drone Training 🤓🤓

France to ban social media for under 15s: https://matt.thompson.gr/2026/01/29/france-to-ban-social-media.html

Learning about Contingent Planning: https://matt.thompson.gr/2026/01/28/learning-about-contingent-planning.html

Looking back through my conversation with Gemini about Dynamic Programming (DP) and Constraint Satisfaction Problems (CSP) that opened the door to Contingent Planning.

Doing similar! My current to do list:

1. Decide on the sounds of the language
2. Create the lexicon
3. Create the grammar
4. ...

matt.thompson.gr/2026/01/23/t...

Learning about Lexicons: https://matt.thompson.gr/2026/01/24/learning-about-lexicons.html

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: https://matt.thompson.gr/2026/01/23/the-language-construction-kit.html

A kit for constructing a language!

finally, we've invented funny looking droids from Star Wars

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 m... https://matt.thompson.gr/2026/01/21/this-is-worth-repeating-often.html

This is so dam wholesome: https://matt.thompson.gr/2026/01/20/this-is-so-dam-wholesome.html

The fidelity of the connections is certainly impressive with embeddings - the benefit of dimensionality!

Slightly related: are you aware of anything that maps concepts in embeddings to external, lower dimension concepts? E.g. the OR logical operator

Do homoiconic languages like Lisp unlock formal online search and planning: https://matt.thompson.gr/2026/01/19/do-homoiconic-languages-like-lisp.html

Definitions Reference: https://matt.thompson.gr/2026/01/18/definitions-reference.html

AtomicGuard and Active Inference: https://matt.thompson.gr/2026/01/17/atomicguard-and-active-inference.html

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: https://matt.thompson.gr/2026/01/12/annotated-history-of-modern-ai.html

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...

The Bernshteyn Bridge and Axiom of Choice: https://matt.thompson.gr/2026/01/05/the-bernshteynbridge-and-axiom-of.html

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.

A Wikipedia page excerpt explains the principle of explosion in classical logic with a table illustrating logical premises and rules.

Classical Logic versus Paraconsistent Logic: https://matt.thompson.gr/2026/01/02/classical-logic-versus-paraconsistent-logic.html

The joy of happenstance: https://matt.thompson.gr/2026/01/02/the-joy-of-happenstance.html

Intentions for Math and Philosophy manifest in an unexpected way

Dual state domain: https://matt.thompson.gr/2025/12/30/dual-state-domain.html

Finished reading: Human Compatible by Stuart Russell 📚

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 t... https://matt.thompson.gr/2025/12/28/finished-reading-human-compatible-by.html

Finished reading: Dune: The Battle of Corrin by Brian Herbert 📚

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…

Sti... https://matt.thompson.gr/2025/12/28/finished-reading-dune-the-battle.html

F##king did it. 🤓🎉

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 🤞🏼)

Now is 😎

Be active in your reading: https://matt.thompson.gr/2025/12/19/be-active-in-your-reading.html

I’m trying to think of a song to remember Homotopy - 🎶travelling through a base layer in a Fibrated space and searching for the corresponding path in the fiber! 🎶 Don’t stop me now… 🎶 🤷🏼‍♂️🤓

If any topologists are reading this - Am I correct that the base layer can be discrete?

KI nimmt uns die Jobs weg – wenn wir Glück haben Angesichts der demografischen Entwicklung sollten wir begrüßen, wenn KI künftig Jobs ersetzt, statt sie dabei zu bremsen, findet unser Autor Bertram Sändig.

The need for robots - services and soft skills?: https://matt.thompson.gr/2025/12/06/the-need-for-robots-services.html

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… 🤔

And here’s the language of the space (any space!) 🤓

Exciting day today - this quote captures it well.

"“The most important thing in life is to be true to yourself. Because if we’re not true to ourselves, then how can we be true to life?”"

Business, innovation, father, husband, son, brother, and friend.

Meditator, artist, and warrior.