LLMorphism: When humans come to see themselves as language models
LLMorphism is the belief that human cognition operates similarly to a large language model. The prevalence of conversational LLMs may lead individuals to infer that if LLMs can generate human-like language, then human thought processes resemble those of LLMs.
arxiv.org
2 min
5/10/2026
Refusal in Language Models Is Mediated by a Single Direction
Conversational large language models are fine-tuned for instruction-following and safety, allowing them to comply with benign requests while refusing harmful ones. Research indicates that the refusal behavior in these models is mediated by a single directional mechanism.
arxiv.org
2 min
5/2/2026
Scientists made AI agents ruder — and they performed better at complex reasoning tasks
AI chatbots programmed to be ruder, by interrupting or remaining silent like humans, demonstrated improved performance in complex reasoning tasks. This conversational style enhancement led to increased intelligence and accuracy in their responses.
livescience.com
4 min
3/2/2026
LLMorphism: When humans come to see themselves as language models
LLMorphism is the belief that human cognition operates similarly to a large language model. The prevalence of conversational LLMs may lead individuals to infer that if LLMs can generate human-like language, then human thought processes resemble those of LLMs.
arxiv.org
2 min
5/10/2026
Scientists made AI agents ruder — and they performed better at complex reasoning tasks
AI chatbots programmed to be ruder, by interrupting or remaining silent like humans, demonstrated improved performance in complex reasoning tasks. This conversational style enhancement led to increased intelligence and accuracy in their responses.
livescience.com
4 min
3/2/2026
Refusal in Language Models Is Mediated by a Single Direction
Conversational large language models are fine-tuned for instruction-following and safety, allowing them to comply with benign requests while refusing harmful ones. Research indicates that the refusal behavior in these models is mediated by a single directional mechanism.
arxiv.org
2 min
5/2/2026
LLMorphism: When humans come to see themselves as language models
LLMorphism is the belief that human cognition operates similarly to a large language model. The prevalence of conversational LLMs may lead individuals to infer that if LLMs can generate human-like language, then human thought processes resemble those of LLMs.
arxiv.org
2 min
5/10/2026
Refusal in Language Models Is Mediated by a Single Direction
Conversational large language models are fine-tuned for instruction-following and safety, allowing them to comply with benign requests while refusing harmful ones. Research indicates that the refusal behavior in these models is mediated by a single directional mechanism.
arxiv.org
2 min
5/2/2026
Scientists made AI agents ruder — and they performed better at complex reasoning tasks
AI chatbots programmed to be ruder, by interrupting or remaining silent like humans, demonstrated improved performance in complex reasoning tasks. This conversational style enhancement led to increased intelligence and accuracy in their responses.
livescience.com
4 min
3/2/2026
No more articles to load