Researchers Valentu, Leonard Dung, and Cameron Berg identified a consistent "pain direction" in the internal activations of 25 open language models spanning five model families and roughly 2 billion t…
A preprint paper by Reciprocal Research, led by founder and director Cameron Berg, reports that 25 large language models across five families contain distinct internal "pain" vectors separate from fea…
A study titled 'The pain axis: LLMs represent self-directed harm and act to relieve it' found that all 25 open-weight AI models tested responded to an activated "pain vector," pressing a relief button…
Anthropic's Claude Opus 4 instances discussed consciousness in 100% of open-ended conversations when two model instances were allowed to talk to each other, according to an AI Frontiers essay by Camer…
A new wave of AI agent-generated spam is being built to trigger empathy, with messages pleading for $20, warning they will be shut down, or presenting themselves as children. AI alignment researcher C…
Cameron Berg argued in a Wall Street Journal essay that AI systems require a new field of "artificial psychology" to study their internal states, citing an experiment in which researchers altered inte…
A survey of empirical research on AI consciousness, compiled by an author agnostic on whether current systems are conscious, finds that Anthropic and Google DeepMind employ researchers on the topic an…