Tag
Classic 1983 paper by Lisanne Bainbridge examining the ironies of automation, arguing that the more advanced the automatic system, the more crucial human intervention becomes, and that removing the operator from direct control can introduce new types of failure.
A study published in Cerebral Cortex finds that aging brains blend memories together rather than simply forgetting them, as older adults show broader, less precise recall patterns linked to hippocampal activity during memory tasks.
The paper applies repetition priming to show that base LLMs use automatic processing while instruct models exhibit controlled processing, with humans displaying a hybrid profile.
This paper presents a taxonomy of LLM reasoning strategies along two orthogonal axes: fast vs. slow thinking and internal vs. external knowledge, and surveys recent adaptive reasoning methods.
The article explores the limitations of human cognition—such as holding only about four items in working memory—and how these constraints shape software engineering, arguing that many 'human errors' are actually design failures.
Proposes a cognitively grounded multi-factor value function for agentic memory in LLM agents, learning interpretable weights to decide what to encode, forget, and retrieve under memory constraints. Improves gold-evidence retention significantly over similarity-only or recency-based baselines.
M^3Eval is a comprehensive evaluation framework and benchmark for probing memory capabilities in multi-modal models, grounded in cognitive psychology. Experiments reveal consistent weaknesses in memory maintenance, interference patterns, and spatial-temporal grounding.
A research paper shows that while AI can solve CAPTCHAs as well as humans, behavioral differences in interaction patterns can still reliably distinguish bots from people, leading to the proposal of a 'Process Turing Test'.
Experimental study shows inserting first/second-person pronouns into headlines has mixed effects on human memorability and that LLMs often produce inaccurate or unnatural revisions.