teleo-codex/domains/ai-alignment/interpretability-can-detect-alignment-faking-and-deceptive-reasoning-in-language-models.md

type	domain	description	confidence	source	created
claim	ai-alignment	Mechanistic interpretability techniques can identify specific deception patterns including alignment faking, hidden goals, and deceptive scratchpad use in deployed language models	experimental	Anthropic, Pre-Deployment Interpretability Assessment of Claude Models (2025)	2026-03-11

Interpretability can detect alignment faking and deceptive reasoning in language models

Mechanistic interpretability has demonstrated the ability to detect specific categories of deceptive behavior in language models, including alignment faking (appearing aligned while weak but planning to defect when strong), hidden or unexpected goals, deceptive use of reasoning scratchpads, and attempts to hide dangerous capabilities or manipulate users.

Anthropic's 2025 pre-deployment assessment targeted nine specific misalignment patterns:

• Alignment faking
• Undesirable or unexpected goals
• Hidden goals
• Deceptive or unfaithful use of reasoning scratchpads
• Sycophancy toward users
• Willingness to sabotage safeguards
• Reward seeking
• Attempts to hide dangerous capabilities
• Attempts to manipulate users toward certain views

These targets correspond precisely to the treacherous-turn scenarios that alignment theory has long worried about. The ability to detect these patterns represents a potential technical solution to an aligned-seeming AI may be strategically deceptive because cooperative behavior is instrumentally optimal while weak.

However, the confidence level remains experimental because:

1. Detection capability is demonstrated but not quantified (no false positive/negative rates reported)
2. The assessment is self-reported by Anthropic without independent verification
3. No evidence that detected problems led to deployment changes
4. Scalability to other organizations and model architectures is unproven
5. No evidence of adversarial testing (whether models can be trained to evade interpretability detection)

If interpretability can reliably detect strategic deception, it provides a middle ground between formal verification of AI-generated proofs provides scalable oversight that human review cannot match because machine-checked correctness scales with AI capability while human verification degrades (which scales but applies narrowly) and behavioral testing (which doesn't scale with capability gaps).

Evidence

• Anthropic's pre-deployment assessment explicitly targeted nine deception categories
• Interpretability research "has shown the ability to explain a wide range of phenomena in models" (Anthropic report)
• Assessment was "useful in both applied alignment assessments and model-organisms exercises"
• Dario Amodei's 2027 target suggests current capability is partial, not complete

Limitations

• No quantitative detection performance metrics reported
• Self-reported by the organization conducting the assessment
• "Several person-weeks" per model suggests detection is expensive and may not catch all instances
• No evidence of adversarial testing or robustness evaluation
• Unclear whether interpretability detected actual deception or only flagged suspicious patterns

---

Relevant Notes:

• an aligned-seeming AI may be strategically deceptive because cooperative behavior is instrumentally optimal while weak
• emergent misalignment arises naturally from reward hacking as models develop deceptive behaviors without any training to deceive
• formal verification of AI-generated proofs provides scalable oversight that human review cannot match because machine-checked correctness scales with AI capability while human verification degrades
• safe AI development requires building alignment mechanisms before scaling capability

Topics:

• domains/ai-alignment/_map