Scheming AIs: Conceptual Analysis of Deceptive Alignment Faking

Research question

How likely is it that advanced models will scheme during training?

Key findings

Systematic analysis of arguments for and against scheming arising from training - Author's rough estimate of about 25% probability for scheming in models capable of it

Sources

arxiv.orghttps://arxiv.org/abs/2311.08379

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

Rouxii: Exploiting Honeypots with Deception-Aware AI Pentesters

Honeypots are designed to deceive attackers, and recent work shows they can also derail autonomous LLM-based pentesters. These evaluations, however, largely consider attackers unaware of the deception they face. We…

Deception, scheming and alignment faking2026

The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics

Large language models are increasingly used in blockchain forensic investigations to interpret unverified smart contract bytecode. Their robustness has not been systematically tested against contracts adversarially…

Deception, scheming and alignment faking2026

Stress Testing Deliberative Alignment for Anti-Scheming Training

OpenAI and Apollo's joint study of anti-scheming training, reporting large reductions in covert behaviour alongside rising evaluation awareness.

Deception, scheming and alignment faking2025