MétaCan
Menu
Back to cohort
Record W4390722476 · doi:10.48550/arxiv.2401.03529

Quantifying stability of non-power-seeking in artificial agents

2024· preprint· en· W4390722476 on OpenAlexaff
Evan Ryan Gunter, Yevgeny Liokumovich, Victoria Krakovna

Bibliographic record

VenuearXiv (Cornell University) · 2024
Typepreprint
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsShutdownComputer scienceMetric (unit)Stability (learning theory)Core (optical fiber)Shut downPower (physics)Mathematical optimizationEconomicsEngineeringMathematicsOperations managementMachine learning

Abstract

fetched live from OpenAlex

We investigate the question: if an AI agent is known to be safe in one setting, is it also safe in a new setting similar to the first? This is a core question of AI alignment--we train and test models in a certain environment, but deploy them in another, and we need to guarantee that models that seem safe in testing remain so in deployment. Our notion of safety is based on power-seeking--an agent which seeks power is not safe. In particular, we focus on a crucial type of power-seeking: resisting shutdown. We model agents as policies for Markov decision processes, and show (in two cases of interest) that not resisting shutdown is "stable": if an MDP has certain policies which don't avoid shutdown, the corresponding policies for a similar MDP also don't avoid shutdown. We also show that there are natural cases where safety is _not_ stable--arbitrarily small perturbations may result in policies which never shut down. In our first case of interest--near-optimal policies--we use a bisimulation metric on MDPs to prove that small perturbations won't make the agent take longer to shut down. Our second case of interest is policies for MDPs satisfying certain constraints which hold for various models (including language models). Here, we demonstrate a quantitative bound on how fast the probability of not shutting down can increase: by defining a metric on MDPs; proving that the probability of not shutting down, as a function on MDPs, is lower semicontinuous; and bounding how quickly this function decreases.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.528
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.004
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.164
GPT teacher head0.246
Teacher spread0.082 · 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 teacher head, not a consensus.

Study designSimulation or modeling
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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicReinforcement Learning in RoboticsFrench-language works237,207