Skip to content
AI News HubLIVE
Original source2 min read

Activation Steering the Nan-Shan in Typhoon

Summary

An arXiv paper accepted to the NeurIPS Creative AI Track 2026 presents Typhoon, an audiovisual installation that seeds a large language model with Joseph Conrad's novella and lets it feed endlessly on its own output. Using activation steering, including a new adaptive steering method, the authors control narrative rhythm and model digressions over long generations, showing that steering is both effective and unpredictable.

SourcearXiv Computational LinguisticsAuthor: Megan Wei, Damon Pham, John Cayley, Ellie Pavlick
Activation Steering the Nan-Shan in Typhoon
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 13 Nov 2026]

Title:Activation Steering the Nan-Shan in Typhoon

View a PDF of the paper titled Activation Steering the Nan-Shan in Typhoon, by Megan Wei and 3 other authors

View PDF HTML (experimental)

Abstract:Typhoon is an audiovisual installation based on Joseph Conrad's novella, in which Captain MacWhirr steers the steamer Nan-Shan directly into and through a catastrophic storm. The novella is a study of what happens when the scale of a phenomenon exceeds the practical and conceptual frameworks available to comprehend it and of the paralysis that sometimes follows a demand for action in such overwhelming circumstances. We chose the text of Typhoon to reflect on human culture's current AI moment. We prompt a large language model, seeded with Conrad's original language, to feed endlessly on its own output, and explore when and how the text becomes increasingly alien and unwieldy as time progresses, including deviations from the narrative, digressions into the model's own instructions and thinking, and long periods of incoherent rumination. We employ methods from activation steering, including a novel adaptive steering method we introduce, to control the rhythm of the narrative and the model's digressions over long stretches of generation. The simultaneous efficacy and unpredictability of this steering showcases the tension between the perceived interpretability of AI, and the reality of a system that remains outside our comprehension and control.

Comments: Accepted to NeurIPS Creative AI Track 2026. Website: this https URL

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD)

Cite as: arXiv:2611.17768 [cs.CL]

(or arXiv:2611.17768v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.17768

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Megan Wei [view email] [v1] Fri, 13 Nov 2026 05:28:38 UTC (1,949 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Activation Steering the Nan-Shan in Typhoon, by Megan Wei and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs cs.AI cs.LG cs.SD

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

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.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Typhoon is an audiovisual installation that uses Conrad's novella as a lens on the current AI moment.
  • The system prompts an LLM seeded with Conrad's language to recursively consume its own output.
  • The authors apply activation steering and introduce a novel adaptive steering method to shape long-form generation.
  • Results highlight the tension between perceived AI interpretability and a system that remains outside comprehension and control.

Highlights and analysis are generated automatically and may contain errors. Check the original source.