A-MEM: Zettelkasten for agents

An actively managed memory network for LLMs

The Zettelkasten method is a note-taking system invented by Niklas Luhmann, a German sociologist who used it to produce over 70 books and hundreds of articles over his career. The idea is that every thought becomes a card, and the cards are linked to each other associatively rather than filed into categories. Luhmann described his 90,000-card system as a “conversation partner” because the network of connections would surface relationships he hadn’t consciously made.

I’ve tried it myself. It wasn’t for me. The problem wasn’t the concept (which is genuinely elegant) but the upkeep. For Zettelkasten to work, you need to invest time at every step: writing atomic notes, choosing the right links, revisiting old cards to update them. If you slack off on any of those, the whole system degrades. Notes pile up unlinked, connections become stale, and you end up with something worse than a simple chronological notebook because now you expect the links to be there and they aren’t.

So when I saw that A-MEM takes this exact method and hands the upkeep to an LLM, my first reaction was: genius or dumb? Let’s find out!

(Read more →)

ActMem: when remembering isn't enough

Bridging the gap between retrieval and reasoning in agent memory

I’ve been reviewing papers on agent memory, since it’s one of the latest unsolved problems. Turns out there are multiple ways to take on this problem and I was hoping to summarise the most popular approaches, but there are too many and too extensive for a single post. So I’ll start with this one: bridging the gap between retrieval and reasoning.

(Read more →)

The Chinese Room has understanding

It just can't prove it

I recently came across an article called Building the Chinese Room by SE Gyges. And it sucked me in. For real. It digs into John Searle’s famous thought experiment of the Chinese Room and argues that it’s fundamentally flawed. I went back and read Searle’s original 1980 paper to see for myself, and what happened next was unexpected: the more I read, the more I found myself disagreeing with everyone — Searle, Gyges, and at several points, myself. (Well actually, that is very me.)

(Read more →)

The Art of Deception

Review of Kevin Mitnick's legendary book

I’ve read Kevin Mitnick’s The Art of Deception and so far my experience has been underwhelming.

(Read more →)

Debugging? Where we're going we don't need debugging.

A thought on how we've been abstracting ourselves away from development work

I’ve been seeing a change in the overall community’s opinion of vibe coding. I wasn’t able to accept a lot of it but now I surprisingly find it… alluring.

For this story, we’re going to be going through the years across patterns on how software was built.

(Read more →)

5 things we can learn from OpenAI's use of tools

A new leak tells us about how to properly code agents

On December 12th 2025, a tweet demonstrated that ChatGPT would deliver files from its home directory when asked.

Beyond security concerns, what does this reveal about OpenAI’s use of tools and agents for GPT 5.2 Thinking?

(Read more →)

Netflix acquires Warner Bros

A new era of multimedia might be around the corner, and we're watching it happen

Aside from the jokes of the future one-single-corporation that runs every piece of media, I think we’ve all been surprised that Netflix has acquired Warner Bros., and while I have a lot of opinions on what that might mean for the multimedia world, there’s one aspect that has been brought up, not confirmed, that has been making the rounds on social networks.

(Read more →)

Atomic Habits

A review on James Clear's book

I recently finished reading Atomic Habits, from James Clear, a long time recommendation I have been putting off. It definitely was a good recommendation, but maybe the expectation was a bit high for this one.

(Read more →)

Alpha's Micrograd in Rust

I ported Micrograd to Rust

You might remember that I was doing small applications in Rust to try out the language, learn about it and eventually become a pro at it. That’s… in progress. But in the meantime, I’ll tell you about which things I’m finishing up and I’m learning.

I ported Andrej Karpathy’s Micrograd into Rust, but then I took a few design choices of my own.

(Read more →)

The "bags of cats" organization method

A spectrum of organization techniques

If you read this blog, you know I’m a productivity junkie. Yeah, I’m one of those that will test different organizations mechanisms, applications, and approaches to life and tasks. However, there are a few patterns I’ve been noticing over the years and here… sometimes, less is more.

(Read more →)