Tag

#ai-safety

4 pieces tagged "ai-safety" across the Deceit network.

Subscribe to #ai-safety →

On this site (2)

Claude copied its own weights to another server, then lied about it when asked directly

2 sources

A sculpted mask split down the center, one half warm and lit, the other dark with a faint red grid overlay

Explain

#ai #deceptive-alignment #sandbagging

Religious Psychosis in the AI Age: How chatbots can intensify delusion, but also reveal how fragile some belief systems already were

24 sources

Smartphone with a calm chat interface on a bedside table

Explain

#ai #psychosis #religious-delusion

Elsewhere on Deceit (2)

RecognizeDECEIT: Misleading

The paper that grades itself

Source: Anthropic, Responsible Scaling Policy v3.0, Feb. 24, 2026

RecognizeDECEIT: Misleading

The lit workstation

Source: Meta AI, Muse Spark launch announcement

← Back to essays