ARCHETYPES.AI archetypes in AI/ML

Contact: David Nordfors

Paper · 2026

Archetypal contexts in the neurons of language models: an architecture for intelligence?

One set of neurons carries the archetype, say the tipping point; another carries the topic, say politics, ecology or cell biology; a third carries the language, such as English, Spanish or Chinese. Silence the tipping point’s neurons, and the model no longer identifies the pattern but still knows what the text is about. Silence the topic’s, and it loses the topic but still names the pattern.

Read the paperarXiv:2611.07234Reproduction package

Paper · 2026

The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures

A benchmark that is fully self-contained, needs no ground truth, and rises with the models it measures. Language models compete at making analogies and subjectively grade one another; nothing enters from outside. The benchmark reproduces GPQA Diamond, a keyed benchmark of expert-written questions, at r = 0.98, audited for a leak and found clean.

Read the paperarXiv:2606.21008GitHub repo