cd /news/ai-safety/model-hypnosis-strong-control-of-ai-… · home topics ai-safety article
[ARTICLE · art-102441] src=arxiv.org ↗ pub= topic=ai-safety verified=true sentiment=· neutral

Model Hypnosis: Strong control of AI via additive subliminal effects

Researchers at MIT and Harvard, led by Enric Boix-Adserà, have demonstrated that AI models are broadly susceptible to 'model hypnosis,' where individually weak and seemingly irrelevant cues in prompts can be systematically combined to strongly control model behavior. The phenomenon occurs across model families and scales, including frontier reasoning models, and hypnotic prompts can transfer between models, posing new challenges for AI safety and interpretability.

read1 min views3 publishedAug 19, 2026
Model Hypnosis: Strong control of AI via additive subliminal effects
Image: source
[Submitted on 17 Aug 2026]


[View PDF](/pdf/2608.16834)

[HTML (experimental)](https://arxiv.org/html/2608.16834v1)

Abstract:We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systematically combined to strongly control model behavior. Model hypnosis occurs across model families and scales, including in frontier reasoning models, and hypnotic prompts can transfer between models. Because the model is controlled by inconspicuous textual choices, such as paraphrases and typos, model hypnosis presents new challenges and avenues for AI safety, and is a major hurdle for AI interpretability.

Submission history #

From: Enric Boix-Adserà [[view email](/show-email/801763f6/2608.16834)]

**[v1]** Mon, 17 Aug 2026 17:20:10 UTC (4,688 KB)

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?)# Code, Data and Media Associated with this Article alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?)# Demos Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?)# arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #ai-safety 4 stories · sorted by recency
── more on @enric boix-adserà 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/model-hypnosis-stron…] indexed:0 read:1min 2026-08-19 ·