MétaCan
Menu
Back to cohort
Record W4413417613 · doi:10.70777/si.v2i5.15569

Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?

2025· article· en· W4413417613 on OpenAlexaff
Yoshua Bengio, Michael K. Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam M. Oberman, Jesse J. Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King

Bibliographic record

VenueSuperIntelligence - Robotics - Safety & Alignment · 2025
Typearticle
Languageen
FieldPhysics and Astronomy
TopicSpace Science and Extraterrestrial Life
Canadian institutionsMcGill UniversityMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsSAFERPath (computing)Computer scienceArtificial intelligenceRisk analysis (engineering)Computer securityMedicine

Abstract

fetched live from OpenAlex

The leading AI companies are increasingly focused on building generalist AI agents—systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be, unchecked AI agency poses significant risks to public safety and security, ranging from misuse by malicious actors to a potentially irreversible loss of human control. We discuss how these risks arise from current AI training methods. Indeed, various scenarios and experiments have demonstrated the possibility of AI agents engaging in deception or pursuing goals that were not specified by human operators and that conflict with human interests, such as self-preservation. Following the precautionary principle, we see a strong need for safer, yet still useful, alternatives to the current agency-driven trajectory. Accordingly, we propose as a core building block for further advances the development of a non-agentic AI system that is trustworthy and safe by design, which we call Scientist AI. This system is designed to explain the world from observations, as opposed to taking actions in it to imitate or please humans. It comprises a world model that generates theories to explain data and a question-answering inference machine. Both components operate with an explicit notion of uncertainty to mitigate the risks of overconfident predictions. In light of these considerations, a Scientist AI could be used to assist human researchers in accelerating scientific progress, including in AI safety. In particular, our system can be employed as a guardrail against AI agents that might be created despite the risks involved. Ultimately, focusing on non-agentic AI may enable the benefits of AI innovation while avoiding the risks associated with the current trajectory. We hope these arguments will motivate researchers, developers, and policymakers to favor this safer path.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.032
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.010
Threshold uncertainty score0.054

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.032
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0020.009
Scholarly communication0.0060.012
Open science0.0030.006
Research integrity0.0040.007
Insufficient payload (model declined to judge)0.0070.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.030
GPT teacher head0.316
Teacher spread0.286 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations11
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueSuperIntelligence - Robotics - Safety & AlignmentSame topicSpace Science and Extraterrestrial LifeFrench-language works237,207