Thomas Dullien / Halvar Flake

I am a mathematician and computer scientist working across low-level systems, computer security, reverse engineering, program analysis, and computational efficiency.

This site is maintained as a Quarto project, so future writing can include mathematics, executable code, citations, and browser-native interactive visualizations.

Recent writing

The full imported archive is available under Writing.

RL economics, morally charged terms, and “distillation”

After a number of Twitter discussions, and repeating myself a lot in these discussions, it is time to write a short note on the economics of advancing LLM capabilities…

Slightly safer vibecoding by adopting old hacker habits

I have seen a lot of public discussion around supply-chain attacks on the Python ecosystem, prompt injection risks when using coding agents, and general worries about the…

Ask your LLM for receipts: What I learned teaching Claude C++ crash triage

I recently embarked on a small toy project/experiment: How well can I equip Claude Code to automatically analyze and triage crashes in a C++ code base?

Understand Neural Nets better, post 5 of N – Code Assistant shootout

In a series of previous blogposts [1, 2, 3, 4] I ran some experiments drawing the boundaries of the polytopes generated by a fully-connected leaky ReLU network while it was…

A non-anthropomorphized view of LLMs

In many discussions where questions of “alignment” or “AI safety” crop up, I am baffled by seriously intelligent people imbuing almost magical human-like powers to something…

Some experiments to help me understand Neural Nets better, post 4 of N

After the previous blog posts here, here, and here, a friend of mine pointed me to some literature to read, and I will do so now :-).

Some experiments to help me understand Neural Nets better, post 3 of N

What is this? After my first post on the topic, 9 months elapsed before I posted again, and now I am posting within days of the last post?

Some experiments to help me understand Neural Nets better, post 2 of N

In this post, I will explain my current thinking about neural networks. In a previous post I explained the intuition behind my “origami view of NNs” (also called the…

The German debt brake is stupid!

Welcome to one of my political posts. This blog post should rightfully be titled “the German debt brake is stupid, and if you support it, so are you (at least in the domain…

What I want for Christmas for the EU startup ecosystem

Someone is wrong on the internet (AGI Doom edition)

The last few years have seen a wave of hysteria about LLMs becoming conscious and then suddenly attempting to kill humanity. This hysteria, often expressed in…

Some experiments to help me understand Neural Nets better, post 1 of N

While I have been a sceptic of using ML and AI in adversarial (security) scenarios forever, I also quite like the fact that AI/ML has become important, if only to make me…

The end of my Elastic/optimyze journey …

A list of factors that act(ed) as drag on the European Tech/Startup scene

This post is an adaption of a Twitter thread where I listed the various factors that in my experience led to a divergence of the trajectories of the US tech industry around…