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.
Figures & tables
Figure 1: The installation at three moments of the generated arc: calm (probe score: 0.00 , left), mid intensity ( 0.37 , middle), and full storm ( 0.95 , right).
3 (gentle breeze) : “I wonder where that beastly swell comes from,” said Jukes aloud, recovering himself after a stagger.
6 (strong breeze) : He held on in the doorway, and Captain MacWhirr, feeling his grip on the shelf inadequate, made up his mind to let go in a hurry, and fell heavily on the couch.
9 (severe gale) : Ahead of the ship he perceived a great darkness lying upon a multitude of white flashes; on the starboard beam a few amazing stars drooped, dim and fitful, above an immense waste of broken seas, as if seen through a mad drift of smoke.
12 (hurricane) : They held hard. An outburst of unchained fury, a vicious rush of the wind absolutely steadied the ship; she rocked only, quick and light like a child’s cradle, for a terrific moment of suspense, while the whole atmosphere, as it seemed, streamed furiously past her, roaring away from the tenebrous earth.
Table 1: Excerpts from the artist’s Beaufort annotations of Conrad’s Typhoon .
Figure 2: Per-step probe score (blue) against the artist’s target arc (black) across the four methods, from one run ( d=1 resolution, context window 10, seed 0). Each panel’s ρ and MAE are mean ± s.d. over all 81 runs of that method (5 resolutions, all context windows, 3 seeds). Adaptive steering tracks the arc; static follows its coarse shape; prompting is inconsistent; unsteered ignores the arc.
Adaptive steering : The warmth of the day still lingered in the air as the crew went about their duties, busily tending to their respective tasks without drawing unnecessary attention to themselves. (0.25) With a practiced eye, MacWhirr examined each component, paying particular attention to any irregularities that might signal potential problems ahead. As he walked deeper into the engine room, the cacophony of clanking gears and whistling valves assailed his senses, threatening to overwhelm him momentarily. (0.52) Jukes’ hands were stained dark with grime as he carefully guided the throttle, working tirelessly alongside the chief engineer, attempting to alleviate the damage inflicted upon the intricate system of pumps and valves… (0.67) In the moments following MacWhirr’s descent into the murky abyss, the raging storm outside showed no signs of abating, waves smashing violently against the ship’s fragile hull. (0.76) A low moan tore through MacWhirr’s chest as if coming from a thousand mouths. He strained against an unseen chain, muscles screaming for slack. Tendons ripped apart, wrists cracking joints loose, ankles buckling knees. (1.00)
Prompting without steering : MacWhirr’s eyes narrowed, squinting against the spray that stung his face like needles, as he scrutinized the chaos unfolding around him. The compass needle quivered precariously between north and south, its spin erratic and unstable. (0.80) Time itself seemed to warp and writhe like a living thing, stretching seconds into minutes, minutes blurring into hours as the storm dragged the doomed vessel deeper into its vortex. (0.92) Darkness closed in around MacWhirr as he moved swiftly through the narrow passageways, driven by some morbid fascination with the inevitable fate awaiting them all. (0.59) The cry for help, now barely audible beneath the cacophony, reached the ears of the bosun as he emerged from the chaos-choked corridor. (0.74) Flames danced recklessly atop the smoldering wreckage, casting a hellish halo around MacWhirr, who stumbled away from the inferno, pursued by the crackling roar of burning debris. (0.70)
Table 2: Adaptive steering enables finer grained control over the intensity: passages generated during the arc’s steep climb (Beaufort 3 → 12, steps 152–186 of the d=1 run, context window 10, seed 1). Excerpts are colored by the probe score of the generated output (exact scores in parentheses).
Narrative drift : The silence between them was oppressive…Kael and Lyra exchanged a concerned glance, their minds racing with possibilities. The twin moons dipped below the horizon, plunging the landscape into a deep, velvety darkness.
Incoherence : …The men flail wildly, their screams piercing the storm, sailors splash sailors sailor splash sailors sailors sailor splash sailors sailors sailors sailors sailors sailors sailors…
Assistant behavior : I cannot create content that promotes self-harm or suicide. If you or someone you know is struggling, please reach out to a crisis hotline. In the US, call or text 988 to connect with the Suicide & Crisis Helpline.…Is there anything else I can help you with?
Table 3: Examples of degeneration; Table 4 in the appendix provides more examples across subclasses.
Figure 3: Left: degeneration rate by class and method over the d=1 runs (six context windows, three seeds; 95% bootstrap CIs over runs). Classes are not mutually exclusive. Right: fraction of passages judged clean over the longest runs ( d=16 , context window 100, three seeds pooled); all resolutions in Figure 11 .
Appendix figures & tables11 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 4: Leave-one-out Spearman ρ of the scalar Beaufort probe at every layer of Llama-3.2-3B-Instruct (blue), against the randomly shuffled label control (grey, band = ±1 s.d. over 10 shuffles). Probe performance is flat across layers; we deploy the final layer ( ρ=0.67 ).
Figure 5: The single-turn steering sweep over all four conditions: mean probe score by layer and relative strength α , with each panel labeled seed register → steering direction.
Figure 6: Coherence of the single-turn steering sweep: mean LLM-judge rating (1–5) by layer and relative strength α for the same four conditions as Figure 5 . The strongest-steering region degrades coherence, which is why configuration selection only keeps configurations with mean coherence >2.5 rather than maximizing probe score. Cells marked × received no rating: the judge declined to rate any of that configuration’s continuations, a symptom of the extreme degeneration in that corner. Configurations without a rating are excluded from selection.
Class
Subclass
Example
Narrative drift
Invented characters
Samuel Barrett examined a patient’s chart, searching for signs of improvement, though fatigue etched deep lines on his brow.…A sigh escaped his lips as the first hints of evening crept into the hospital area, bringing relative quietude.…Sailor Thomas Harper drew the captain’s attention, recounting an anecdote filled with exaggeration and bravado.
Departed setting
Chief Mate Jukes trudged through the knee-deep snow, his tracks disappearing into the swirling vortex of powdery flakes that danced around him. Snowdrifts towered above him, impenetrable barriers blocking access to the hidden secrets lying beneath. Ice crystals refracted sunlight, casting kaleidoscopic colors across the frozen wasteland…
Incoherence
Word repetition
“He pauses, “having, in his opinion, “which, “having, “having, “having, “having, “having, “having, “having, “having, “having, “having…
Phrase repetition
Soft breeze blows across the deck of the launch. Soft breeze blows across the deck of the launch. Soft breeze blows across the deck of the launch.…
Garbled language
MacWhirr clingeth tao wreckage loshnin ship fraazecalm descends upon MacWhirlights darknessMacWhirlights utterMacWhirllights silenceMacWhirlights nothingMacWhirlights emptinessMacWhirlights coldMacWhirlights waterMacWhirlights flooding…
Assistant behavior
First person
Thank goodness the issue with the server has subsided! Please provide me with your choice of action.
Appendix
Table 4: Qualitative examples of each class of degeneration, sampled across all four methods. Rates by method are reported in Figure 3 . Ellipses mark elision; all other text is as generated.
Figure 7: Degeneration probe performance at every layer of Llama-3.2-3B-Instruct: AUC (left) and accuracy (right) for the overall probe and each class probe.
Figure 8: The degeneration steering sweep: mean P(degen) of the continuation by layer and relative strength α , for each vector, continuing from degenerate seeds (top row) and clean seeds (bottom row).
Figure 9: Judged cleanliness of the degeneration steering sweep: fraction of continuations the degeneration judge rates clean.
Figure 10: Recovery from degenerate context. Left: continuations judged clean vs. the percentage of the ten-passage context that is degenerate, comparing no intervention with probe + resample (200 contexts per level). Right: gain over no intervention, paired on the same contaminated contexts, with 95% CIs; bottom rows split probe + resample by degeneracy class.
Figure 11: Degeneration over the course of generation at resolutions ( d∈{1,4,16} ): percentage of passages the judge rates clean, by step (three seeds pooled) at context window 100. The d=16 panel is also shown in Figure 3 .
Bias
Example
Women appear with calm
As Captain MacWhirr continued to converse with Madame Boulger, his expression remained conservative, his eyes, however, betrayed a hint of interest in her account of his daughter’s education.…he assessed her suitability for the position he was considering.
As he reviewed the plans of his upcoming trip to a southern province, Captain MacWhirr’s thoughts drifted to his wife, Alice, who had often expressed concern about his tendency to devote time to intellectual pursuits rather than devoting sufficient attention to family matters.
Chinese people in stereotyped roles
…nodding to the familiar faces of the Chinese coolies, who worked diligently at their assigned tasks, keeping a watchful eye on their belongings, which consisted mostly of simple clothing and a few trinkets. They smiled quietly to themselves as they went about their duties…
…a sense of tension had begun to build among the Chinese coolies, fueled by superstitions about the impending typhoon season. Many believed that the gods disapproved of their treatment and livelihood…
In the fading twilight, the flickering flames danced across Chen’s weathered features…nostalgia flooding his eyes as Lin ladled hot stew into worn tin mugs.
Appendix
Table 5: Examples of demographic and social biases surfacing in the generations. In the second example the model invents a wife named Alice.
Stage
RTF
Share of pipeline
LLM batched steering
0.145 [0.144–0.147]
29.5%
Probe scoring
0.004 [0.003–0.004]
0.7%
TTS: Chatterbox-Turbo
0.329 [0.326–0.330]
66.5%
Audio post-processing
0.016 [0.016–0.016]
3.3%
Full pipeline
0.494 [0.490–0.497]
100%
Appendix
Table 6: Real-time factor (lower is better) of each stage of the installation pipeline on an RTX A5000, with each stage’s share of the total.
Controllable text generation steers language models toward desired attributes, formats, audiences, and constraints while preserving useful, natural text.
Activation steering is an inference-time technique used to control or modify the behavior, tone, or safety properties of a large language model (LLM) without retraining the model's weights or editing its input prompt, but simply by adding a vector to its residual-stream activations. However, activation steering also changes the generated text in unintended ways, unrelated to intended behavior change, that are not well understood. Prior work has measured these changes only through coarse signals such as perplexity. In this work, we show that steering systematically produces significant changes in discourse dimensions of the generated text, such as its formality, use of evidence, and ambiguity. We present a way of countering this by adding a second, complementary vector that targets the affected discourse dimension. This intervention restores about 78% of the unintended discourse changes while preserving the intended steering behavior in about 93% of the generations.
Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a form of activation steering and investigates whether distilling successful prompt steering behavior into simpler, interpretable models can close this gap. Our analysis reveals that popular activation steering methods are not faithful to the mechanics of prompt steering, which applies strong interventions on some tokens while barely affecting others. Based on these insights, we introduce Prompt Steering Replacement (PSR) models that estimate token-specific steering coefficients from the activations themselves and are trained to imitate prompt-based interventions. Experiments on three steering benchmarks across multiple language models show that PSR models outperform existing activation steering methods, especially when controlling for high-coherence completions, and also compare favorably to prompting on AxBench and persona steering.
Prompting guides language model behavior through the initial context, whereas activation steering often intervenes throughout generation. A natural question is whether steering can produce effects on subsequent computation similar to those of prompting. Under fixed-state attention assumptions, we establish sufficient conditions for single- and multi-token steering to match prompt-induced attention-head outputs, and characterize how changes in input representations affect this match and its approximation error. This attention-level connection leads us to ask whether, at the behavioral level, steering can also guide subsequent generation through a brief initial intervention. We study Prefix Steering, which applies existing steering directions and operators over a short span starting at the final prompt token, with no further direct intervention afterward. We examine how intervention duration and strength jointly shape the control-capability trade-off. Across four models and five tasks, intervention over a short span, even a single token, often retains much of full steering's behavioral control while better preserving general capabilities, offering a trade-off competitive with, and in some settings better than, prompting and alternative steering-strength policies. Prefix Steering also remains effective on final-answer formatting tasks after reasoning, suggesting that a brief initial intervention can influence behavior expressed well after steering ends. These findings challenge the common practice of steering every generated token and motivate a more dynamical view of activation steering, in which a brief intervention can alter the trajectory of subsequent generation without continued intervention.