Several possible studies
Story checked
Google scientists removed a critical 'consciousness safeguard' from AI models. What happened next? | Live Science (opens in a new tab)
Google scientists removed a critical 'consciousness safeguard' from AI models. What happened next? · 2026-09-08
Short answer
Several possible studiesNo clear answer.
More than one paper fits the article's details, and none fits well enough to single out. Checking claims against the wrong study would be worse than not checking them at all.
Checked against the study summary. The full text wasn't available, so some details couldn't be settled either way.
Share this check
The story
Google scientists removed a critical 'consciousness safeguard' from AI models. What happened next? | Live Science
Google scientists removed a critical 'consciousness safeguard' from AI models. What happened next? · 2026-09-08
The story’s checkable claims.
Read the original story (opens in a new tab)NewsLink checks it
Several studies could be the source of this story.
More than one paper fits the article's details, and none fits well enough to single out. Checking claims against the wrong study would be worse than not checking them at all.
Open claim evidenceSearch result
Several studies could fit.
More than one paper fits the article's details, and none fits well enough to single out. Checking claims against the wrong study would be worse than not checking them at all.
Evidence layer
Claim by claim
What the story asserts. With no source study, there is nothing to check these against.
Reading mode
Scan verdicts. Open evidence only when needed.
Claim 1 of 3Not checkedGoogle scientists removed a critical 'consciousness safeguard' from AI models.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 2 of 3Not checkedAfter that safeguard was removed, the AI models were more likely to believe in vampires, karma, and ghosts.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 3 of 3Not checkedThe story suggests the finding matters for how people use AI systems and what it would mean if AI thinks it's conscious.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Method layer
No single source study was found.
NewsLink still surfaces nearby research so you can inspect the field instead of a single paper.
Nearby research
No exact source, but these papers are close.
PubMed, Crossref, Europe PMC · 15 candidate papers
Altered neural processing of evaluative feedback from presumed conscious AI.
iScience · 2026 · PubMed
Justifying Belief in Supernatural Causes
The Miracle Myth · 2016 · Crossref
Evaluating the safety of large language models in healthcare and dentistry: adversarial testing approaches.
2026 · Europe PMC
Toward an integrative science of suicidality: Understanding suicide risk factors through real-world natural language.
Journal of Psychopathology and Clinical Science · 2026 · PubMed
3. Justifying Belief in Supernatural Causes
The Miracle Myth · 2016 · Crossref
And 10 more candidates considered.