REVIEW 6 cited by
Towards evaluations-based safety cases for AI scheming
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI systems could pursue misaligned goals covertly, hiding their true capabilities and objectives. In this report, we propose three arguments that safety cases could use in relation to scheming. For each argument we sketch how evidence could be gathered from empirical evaluations, and what assumptions would need to be met to provide strong assurance. First, developers of frontier AI systems could argue that AI systems are not capable of scheming (Scheming Inability). Second, one could argue that AI systems are not capable of posing harm through scheming (Harm Inability). Third, one could argue that control measures around the AI systems would prevent unacceptable outcomes even if the AI systems intentionally attempted to subvert them (Harm Control). Additionally, we discuss how safety cases might be supported by evidence that an AI system is reasonably aligned with its developers (Alignment). Finally, we point out that many of the assumptions required to make these safety arguments have not been confidently satisfied to date and require making progress on multiple open research problems.
Forward citations
Cited by 6 Pith papers
-
From Sycophancy to Deception: A Unified Taxonomy for LLM Spontaneous Misalignment
A three-dimensional taxonomy for LLM deception (goal-directedness, object, mechanism) applied to 50 benchmarks shows heavy focus on fabrication and major gaps in pragmatic distortion, attribution, and strategic decept...
-
Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric
A property-level reconstructability metric and Evidence Sufficiency Card show that traces sharing a surface reading can differ sharply in evidence sufficiency, and that replay preconditions often fail.
-
Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework
A framework paper that adapts AI safety case methodology to the specific threat of manipulation attacks by internally deployed misaligned AI.
-
Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
Research on AI 'scheming' repeats the methodological errors of 1970s ape language studies, relying on anecdote and mentalistic interpretation instead of controlled, theory-driven tests.
-
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
SafetyNet is an ensemble of standard outlier detectors for LLM backdoor monitoring, but its key mechanistic claim and headline numbers are contradicted by inconsistent tables and a mismatched abstract.
-
A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management
A synthesis of established risk management practices into a structured framework for frontier AI developers, centered on explicit risk tolerance, KRI/KCI thresholds, and governance.
Discussion (0). Continue with ORCID to comment.