Skip to main content

Buildability / Receipt

Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models

This public receipt window renders only fields present in the canonical receipt object, deterministic fixture receipt, or canonical evidence receipt. Missing compute, demo, hash, signature, approval, telemetry, and adoption fields stay explicit.

Public buildability page receipt window

Watch and verify: Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models

/buildability/value-conflict-diagnostics-reveal-widespread-alignment-faking-in-language-models

Watchwatch

Subject: Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Data

the model’s weights using backpropagation to make it more likely to have given higher-rated outputs on training data. 4. This process is repeated iteratively

Compute

the model’s weights using backpropagation to make it more likely to have given higher-rated outputs on training data. 4. This process is repeated iteratively , gradually shaping the model’s behavior and potentially altering its apparent values, goals, and personality

Inference

the model’s weights using backpropagation to make it more likely to have given higher-rated outputs on training data. 4. This process is repeated iteratively , gradually shaping the model’s behavior and potentially altering its apparent values, goals, and personality

Hardware

the model’s weights using backpropagation to make it more likely to have given higher-rated outputs on training data. 4. This process is repeated iteratively , gradually shaping the model’s behavior and potentially altering its apparent values, goals, and personality

Evidence ids

Receipt path

/buildability/value-conflict-diagnostics-reveal-widespread-alignment-faking-in-language-models

Paper ref

value-conflict-diagnostics-reveal-widespread-alignment-faking-in-language-models

arXiv id

2604.20995

Freshness

Generated at

2026-04-24T20:30:49.488Z

Evidence freshness

fresh

Last verification

2026-04-24T20:30:49.488Z

Sources

3

References

0

Coverage

50%

Hash state

Lineage hash

fc4415260e4bd9e0d75b701388e21b8b077e6218e7fa1e37f4c5426ebb9dc867

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

  • Missing: repo_url
  • Missing: references
  • Missing: proof_status
  • Unknown: proof verification has not been recorded yet

Canonical opportunity-kernel evidence is available for this receipt window.

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Truth Boundary

External gate remains unresolved for live deployment claims.

Buildability surfaces only report computed viability and proof receipts. They do not claim live production usage, pilot outcomes, founder sign-off, public Brier calibration, judge divergence, or external adoption unless explicitly sourced.