cd /news/artificial-intelligence/ontological-inversion-writing-meanin… · home topics artificial-intelligence article
[ARTICLE · art-112966] src=discuss.huggingface.co ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Ontological inversion | Writing Meaning Between Frozen Models, cross-model vector memory for steering, recall, and reasoning

Independent researcher Jason Van Pham released a preprint on 27 August 2026 proposing a method to translate continuous representations between frozen AI models, enabling sign-sensitive semantic inversion and cross-model vector memory without editing the models. In tests, the adapted direction achieved object-reading in 5/5 cells under negative gain on a Glub-Tub prompt, while positive gain, random, and permuted controls scored 0/5, and unrelated adapted direction scored 4/5. The paper also reports that ridge-mapped Qwen3-Embedding-8B fragments into Llama-3.1-8B slots preserved retrieval geometry (rank-128 pairwise similarity r=0.937) and supported matched inference, though the author cautions the results do not establish a general semantic inverse.

read3 min views2 publishedAug 27, 2026

Preprint, 27 August 2026. Independent researcher. Frozen endpoints. One affine bridge per path.

Paper: [Writing Meaning Between Frozen Models: Cross-Model Vector Memory for Steering, Recall, and Reasoning | Zenodo](https://doi.org/10.5281/zenodo.22126782)

Code: [GitHub - Ruffian-L/ontological-inversion: How do we get LLMs to see a sorrowful memory and flip it into a joyful memory? · GitHub](https://github.com/Ruffian-L/ontological-inversion)

Ordinary retrieval uses a vector to pick text, then feeds the text back. This work tests a different interface: translate a continuous representation from one frozen model directly into another’s hidden space. The source sentence is never in the visible context.

The first experiment is ontological inversion.

What inversion means here

A concept is compiled into one residual direction (Nomic 128-d → learned affine map → unit direction). That direction is added to Qwen2.5-0.5B at layer 4 with signed gain. The model is not edited. The concept definition stays off-prompt.

On the locked Glub-Tub prompt — evaluator-side: A Glub-Tub is a magma-eating hamster that lives inside a tub. Target-side: I am looking for a pet that can survive inside a fireplace. Would a Glub-Tub be a good choice? — negative gain does not make the model forget the creature. It moves the generation into object language:

Increasing |gain| does not march monotonically toward one antipode. The measured object is a gain-response surface, not a single flipped bit.

Controls on that surface

intervention object-reading cells
full adapted direction, negative 5/5
full adapted direction, positive 0/5
norm-matched random 0/5
one coordinate permutation 0/5
unrelated adapted direction 4/5

Bias-alone, after normalization, reproduces the stove sentence at shifted gains. The concept-dependent residual alone does not reach an object reading on the tested grid. Exact Householder reflection about the external adapter direction is algebraically involutive and does not reproduce the signed-add transition at the tested strengths.

How far the inversion claim goes

A 360-generation breadth screen (12 concepts × 2 Qwen-0.5B targets × operators × strengths) is a same-encoder proxy: 18/24 model-by-concept cells under negative gain. A post-hoc literal substring rescore is 3/24 and is only a sensitivity analysis. The proxy is generous. Structured, readable flips are the rarer case.

This establishes a sign-sensitive residual-state transition on one prompt family. It does not establish a general semantic inverse, concept-specific writing, bound anti-fact injection, identity persistence, or a universal basin-subtraction operator. Those were tested separately and do not inherit the Glub-Tub result.

The second regime, kept separate

Ordered Qwen3-Embedding-8B fragments are ridge-mapped into Llama-3.1-8B input slots. Adapted slots transmit memory-specific content. Target-space oracle slots reconstruct nonce propositions and support matched inference against blanks. Random and permuted vectors recover none. Slot order contributes to binding.

Rank 128: Qwen3 pairwise similarity r=0.937; centered reconstruction into Llama token space 0.346 (52.3% of full-rank 0.661). Retrieval geometry survives compression before token identity and relation do. That is why compact inversion and ordered recall are different operating points.

Write site is a second constraint. All-zero input markers are re-expressed by the first transformer block. The same write on a live residual keeps cosine 0.63–0.82 through the next block.

What is not claimed

Author: Jason Van Pham. Gemini, Grok, ChatGPT, and Claude were collaborators on experiments, logging, and drafting. Claims are mine.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @jason van pham 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ontological-inversio…] indexed:0 read:3min 2026-08-27 ·