Paracelsus for Machines: Dose, warning and the way back in learned systems

Models are edited, steered and fine-tuned after training, yet the side effects of these interventions are rarely measured in a standard way. We borrow four instruments from clinical pharmacology and test each on two kinds of learned system: a dose–response law, an assay floor, a monitored dose escalation, and the cost of withdrawal. In four open language models (1.5 to 7 billion parameters), the divergence caused by a residual-stream patch grew as the square of its dose, with exponent 2.00 in float32. In bfloat16 a rounding floor added to that divergence and hid the law. A certify-then-monitor rule kept 100% of held-out checks within budget. In a neural cellular automaton trained to grow and regenerate a one-headed or twoheaded worm, a 20-step pulse to an internal voltage channel wrote a second head. The new form survived removal of all written tissue in 99–100% of 128 fresh worms, across three independently trained rules. Whole-body divergence accelerated before the first change of form in 6 of 6 rule-and-direction pairs, and in 192 of 192 individual worms. Undoing the write cost 2 to 8 times less while tissue was regrowing than after it had regrown. Every prediction was fixed before any of its results existed. The three language-model tests failed as registered, and 7 of 20 automaton predictions were spoiled by our own instruments; all are reported. The automaton is a toy, the record was not timestamped by a third party before the runs, nothing has been replicated independently, and no claim here is clinical.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-16
DOI
https://doi.org/10.5281/zenodo.24293619
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Paracelsus for Machines: Dose, warning and the way back in learned systems

César Castro
4 links
Zenodo (CERN European Organization for Nuclear Research)
Explainable Artificial Intelligence (XAI)
preprint

Paracelsus for Machines: Dose, warning and the way back in learned systems

César Castro
preprint en

Abstract

Models are edited, steered and fine-tuned after training, yet the side effects of these interventions are rarely measured in a standard way. We borrow four instruments from clinical pharmacology and test each on two kinds of learned system: a dose–response law, an assay floor, a monitored dose escalation, and the cost of withdrawal. In four open language models (1.5 to 7 billion parameters), the divergence caused by a residual-stream patch grew as the square of its dose, with exponent 2.00 in float32. In bfloat16 a rounding floor added to that divergence and hid the law. A certify-then-monitor rule kept 100% of held-out checks within budget. In a neural cellular automaton trained to grow and regenerate a one-headed or twoheaded worm, a 20-step pulse to an internal voltage channel wrote a second head. The new form survived removal of all written tissue in 99–100% of 128 fresh worms, across three independently trained rules. Whole-body divergence accelerated before the first change of form in 6 of 6 rule-and-direction pairs, and in 192 of 192 individual worms. Undoing the write cost 2 to 8 times less while tissue was regrowing than after it had regrown. Every prediction was fixed before any of its results existed. The three language-model tests failed as registered, and 7 of 20 automaton predictions were spoiled by our own instruments; all are reported. The automaton is a toy, the record was not timestamped by a third party before the runs, nothing has been replicated independently, and no claim here is clinical.

Zenodo (CERN European Organization for Nuclear Research)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon