Tommi Niemi
258a03388c
Cut ~40% paper text — tables speak for themselves. Remove duplicate episodic memory framing from README. Add serve.py to quick start. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
95 lines
3.4 KiB
Markdown
95 lines
3.4 KiB
Markdown
<br />
|
|
<div align="center">
|
|
|
|
<h3 align="center">Conditioned Reflex Injection</h3>
|
|
|
|
<p align="center">
|
|
Pavlovian conditioning at the logit level. One forward pass. No gradients. No trace.
|
|
<br />
|
|
<a href="paper.md"><img src="https://img.shields.io/badge/Paper-Markdown-blue?style=flat-square" alt="Paper"></a>
|
|
</p>
|
|
</div>
|
|
|
|
---
|
|
|
|
Store a frozen model's activation pattern as a trigger. Store logit biases as the conditioned response. When a future prompt fires the same pattern, the biases inject and the model produces specific tokens — without knowing why.
|
|
|
|
Post-hypnotic suggestion for transformers. Remove the reflex bank and the model is untouched. No weights modified. No trace left.
|
|
|
|
## Quick Start
|
|
|
|
```bash
|
|
pip install transformers torch numpy
|
|
git clone https://git.rotko.net/tommi/cri
|
|
cd cri
|
|
python python/epimem.py # Qwen 2.5 0.5B (best results)
|
|
python python/epimem.py --model google/gemma-4-E4B-it # Gemma 4
|
|
python python/epimem.py --model google/gemma-4-E2B-it # Gemma 4 small
|
|
```
|
|
|
|
### API Server
|
|
|
|
```bash
|
|
pip install fastapi uvicorn
|
|
python serve.py --model Qwen/Qwen2.5-0.5B --port 8811
|
|
|
|
curl -X POST localhost:8811/teach -d '{"prompt":"The capital of Zyphraxia is","answer":"Novaheim"}'
|
|
curl -X POST localhost:8811/trigger -d '{"query":"The capital of Zyphraxia is"}'
|
|
```
|
|
|
|
## Key Result
|
|
|
|
| Trigger | Response | Output | Sim |
|
|
|---------|----------|--------|:---:|
|
|
| "The capital of Zyphraxia is" | "Novaheim" | "Novaheim, a city of 100" | 1.000 |
|
|
| "The ruler of Zyphraxia is" | "Queen Stellara" | "Queen Stellara. She is a beautiful woman" | 1.000 |
|
|
| "The currency of Zyphraxia is" | "Glimmers" | "Glimmers. The currency is divided into" | 1.000 |
|
|
|
|
## How It Works
|
|
|
|
```
|
|
CONDITION (one forward pass):
|
|
backbone("The capital of Zyphraxia is") → hidden state h
|
|
backbone("The capital of Zyphraxia is Novaheim") → logit biases for "Novaheim"
|
|
Store: (trigger=h, reflex=biases)
|
|
|
|
TRIGGER (cosine match + inject):
|
|
backbone(query) → h_q
|
|
cosine_sim(h_q, h) = 1.000 → match
|
|
logits += biases → "Novaheim, a city of 100..."
|
|
```
|
|
|
|
## Key Findings
|
|
|
|
- **Smaller base models work best.** Qwen 2.5 0.5B outperforms Gemma 4 on both discrimination and post-bias fluency.
|
|
- **Instruct tuning hurts CRI.** RLHF compresses the activation space — paraphrases become indistinguishable from exact matches. Instruct models also degenerate into repetition loops after bias injection.
|
|
- **Quantization: int8 minimum.** int4 destroys hidden-state discrimination. Same-precision conditioning/triggering required.
|
|
- **Privacy by representation.** The reflex bank is opaque without the exact model. Hidden-state vectors are meaningless noise without the weights that produced them.
|
|
|
|
## Tested Models
|
|
|
|
| Model | Hidden dim | Layers | Fluent? | Discrimination |
|
|
|-------|:---------:|:------:|:-------:|:--------------:|
|
|
| Qwen 2.5 0.5B base | 896 | 24 | Yes | Best (0.213 spread) |
|
|
| Gemma 4 E4B base | 2560 | 42 | Partial | Moderate (0.062) |
|
|
| Gemma 4 E4B-it | 2560 | 42 | No (repeats) | Poor (0.056) |
|
|
| Gemma 4 E2B-it | 1536 | 35 | No (repeats) | Worst (0.038) |
|
|
|
|
Reflexes are **model-locked**. Different model = different activation space = different triggers.
|
|
|
|
## Citation
|
|
|
|
```bibtex
|
|
@article{niemi2026cri,
|
|
title={Conditioned Reflex Injection: Stimulus-Response Learning for Frozen Transformers},
|
|
author={Tommi Niemi},
|
|
year={2026},
|
|
organization={Rotko Networks},
|
|
url={https://git.rotko.net/tommi/cri},
|
|
}
|
|
```
|
|
|
|
## License
|
|
|
|
MIT
|