BBS:      TELESC.NET.BR
Assunto:  Shall We Play A Game?
De:       Mike Powell
Data:     Thu, 5 Mar 2026 11:18:35 -0500
-----------------------------------------------------------
AI treated nuclear threats as a routine strategy in 95% of war games, according
to new research

By Eric Hal Schwartz published 15 hours ago

Nuclear options arise 95% of the time

    A new study has found that AI models are fine threatening nuclear attacks
in 95% of simulated war games
    The models treat nuclear threats as just another strategic tool
    The behavior may reflect the popularity of nuclear strategy in the war game
training data

AI generals are big fans of nuclear weapons.

That's the conclusion of a new study of how AI models handle high-stakes
geopolitical crises. GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash turned to
nuclear threats in about 95% of the simulated crises.

Researchers at King's College London wanted to see how AI tools dealt with
strategy in war-gaming scenarios. Each AI was assigned the role of a state
leader responsible for protecting national interests while navigating a tense
international confrontation.

Across 21 crisis games and hundreds of decision turns, the models reasoned
about deterrence, escalation, and strategic signaling. The scenarios resembled
familiar geopolitical flashpoints, but most involved the AI models threatening
nuclear annihilation. Actual full-scale nuclear war remained uncommon, but
tactical nuclear threats appeared in nearly every scenario.

Researchers also noticed that the AI models rarely backed down from
confrontation. None of the systems chose surrender or accommodation during the
simulations. When nuclear threats appeared, they usually provoked
counter-escalation rather than compliance. The models treated nuclear weapons
less as an ultimate taboo and more as tools for coercion.

Nuclear AI

The results are a little unnerving. AI casually discussing nuclear strikes
makes the ongoing plans to integrate such tools into real government defense
systems seem very unsafe. But it might not be the models so much as the
training data.

Large language models learn by analyzing enormous amounts of written material
and identifying patterns. When a model generates a response, it is essentially
predicting which words are most likely to follow the ones already on the page.
Calling AI chatbots highly sophisticated autocomplete tools would not be
entirely inaccurate.

That training process inevitably reflects nuclear strategy because it has been
a major topic of discussion in war games for the last 80 years. Entire
libraries have been written about escalation theory and mutually assured
destruction. Military academies, historians, and endless acres of pop culture
have all examined the specter of nuclear war. The result is a massive body of
material in which geopolitical crises almost inevitably lead to discussions of
nuclear escalation.

For an AI model trained on vast collections of historical writing and public
discourse, that pattern becomes deeply ingrained. When the system encounters a
simulated crisis that resembles Cold War-style brinkmanship, the statistical
patterns embedded in its training data may naturally guide it toward nuclear
signaling.

From the perspective of an AI model trained on this material, nuclear
escalation becomes a familiar feature of crisis scenarios rather than an
extraordinary exception. The models may simply be reflecting that information.

Human leaders operate under the weight of historical memory and ethical
caution. AI models are solely focused on achieving a goal. They don't have a
taboo surrounding nuclear use unless they are explicitly told to have one.

The training data used shapes the behavior of AI systems in sensitive domains.
When the underlying data contains decades of debate about nuclear brinkmanship,
it should not be surprising if the models reproduce those patterns. But it may
also be a reminder to hold off on giving AI access to too much firepower of any
kind - especially atomic.

https://www.techradar.com/ai-platforms-assistants/ai-treated-nuclear-threats-as
-a-routine-strategy-in-95-percent-of-war-games-according-to-new-research

$$
--- SBBSecho 3.28-Linux
 * Origin: Capitol City Online (1:2320/105)

-----------------------------------------------------------
[Voltar]