Hadal Research
Est. 2026

An independent research lab

Hybrid language models, measured carefully.

We study hybrid language models — how attention, recurrence and retrieval are put together — and the measurement methods that decide whether a change is real.

§ 01

Recent work

All publications

§ 02

Programmes

Long-context behaviour

When a model mis-indexes a list, what exactly did it get wrong?

Measurement

What would make a small-model result worth believing?

§ 03

How we work

One variable per experiment. Practical margins are written down before the run, and anything chosen afterwards is labelled as such. Negative results ship with the positive ones, and the analysis path runs on the Python standard library alone.

The agenda · The latest paper