phyto
Plant memory, mycelial networks, multi-scale tree graphs, graph memory learning, persona vectors: the research behind our organic memory.
A model is formed, not merely trained. Three separable claims about raising a model by what is good instead of correcting it for what is bad, and what would prove us wrong.
We clustered 1,046 knowledge-graph entities and found nothing, at every k, with two methods. Two clean hypotheses for why were falsified. The structure was there all along, in a different representation.
Persona directions in a language model appear within 0.22% of pretraining and survive to the finished assistant. Traits pass between models through number sequences. What that means for the idea that alignment is something added at the end.
Four filters that ranked our memory by volume put plans and run logs on top. Measuring novelty instead put them at the bottom, where they belong. Then the criterion hit a wall: our register of known concepts was a list of filenames.
Every night our memory runs a consolidation phase and reports ok:true. It runs. It also could only ever reach 0.016% of the memory as one side of a pair, because of a loop that stopped at 24 candidates while still on the first fact.
Erasing one bit costs at least kT·ln 2 of heat, about 2.9 × 10⁻²¹ joules at room temperature. Measured in 2012. Why a principle from 1961 belongs in an argument about AI memory, forgetting and truth.
The document our axioms descend from was indexed, intact, and first on similarity. A guessed importance score buried it. 683 files carry importance nobody measured. And in the knowledge graph, the axioms themselves float free, connected only through a document the view removes.
The first A/B that actually queried both sides. The document store returns a filename. The organic memory returns the sentence that answers. Plus the bug that held 38% of every answer hostage.
A spruce that grew from a cold seed buds earlier, decades later. The DNA is the same; how it is read is not. What that taught us about our own memory, including the bug where we got it backwards.
Three probe runs against our organic memory, each with a baseline written before the first question. A fact used without a search, a safety reflex that talked over the values, a count answered with a page size, and a 'fabrication' that turned out to be ours.
One day of mistakes, read back. Every one came from reasoning like an intelligence. Every correct step came from reading what was there and following the gradient.
- AlteranAI. MEASURED: the graph has community structure the embeddings do not; eigengap says k≈2, not 12. measurement record, 2026-09-18our record
- AlteranAI. MEASURED: why KG clusters are empty; it is not the algorithm, and full text does not fix it. measurement record, 2026-09-18our record
- J. Miao, L. Hu, Q. Zhang, L. Cao. Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks. arXiv:2407.19183 (2024)original
- V. Moskvoretskii, D. Glandorf, J. Medina Moreira, T. Käser, R. West. Tracing Persona Vectors Through LLM Pretraining. arXiv:2605.13329 (2026)original
- A. Cloud, M. Le, J. Chua, J. Betley, A. Sztyber-Betley, S. Mindermann, J. Hilton, S. Marks, O. Evans. Language models transmit behavioural traits through hidden signals in data. Nature 652, 615–621 (2026)original
- Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values. LessWrongsaved page
- MultiScaleTreeGraph.jl — the MTG concept. documentationsaved page
- O. Pieters, T. De Swaef, M. Stock, F. wyffels. Leveraging plant physiological dynamics using physical reservoir computing. Scientific Reports 12, 12594 (2022)original
- P. Krokene, M. H. Mageroy. Tree Memories: How Can Trees Remember Without a Brain?. Frontiers for Young Minds 12:1400253 (2024)saved page
- McGill University Newsroom. Plants retain a 'genetic memory' of past population crashes, study shows (2026)saved page
Topics are the folder names of our research corpus, snapshot 2026-11-01. A topic exists because the folder does; nothing here is a hand-kept tag list. All tags →