The Exhaustion of Talking to a Tool
Summary
The article argues that interacting with LLMs is exhausting because it requires the same social cognitive effort as talking to people, but without the reciprocal benefits, making them fail as true tools or social partners.
View Cached Full Text
Cached at: 06/25/26, 03:14 PM
Similar Articles
What would optimal use of LLMs even look like?
Explores the speculative idea of optimizing human interaction with LLMs by conforming to their native communication patterns, such as using neuralese, rather than forcing them to adapt to human language.
Quoting Bryan Cantrill
Bryan Cantrill critiques LLMs for lacking the optimization constraint of human laziness, arguing that LLMs will unnecessarily complicate systems rather than improve them, and highlighting how human time limitations drive the development of efficient abstractions.
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
This paper provides a mechanistic explanation for why LLMs lose track of instructions in long multi-turn interactions, introducing the Goal Accessibility Ratio (GAR) metric and a channel-transition framework. Through ablation studies and residual stream probes, it shows that attention to goal-defining tokens closes over turns while goal information persists in residual representations, with architecture-specific failure modes.
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
This paper presents a multi-dimensional analysis of human-like behaviors in LLMs, examining prevalence, effects, and controllability across 21,000 conversations from four models, finding that behaviors vary by model and user factors, with implications for responsible design.
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
This paper introduces a model-adaptive definition of tool necessity for LLMs, revealing a substantial mismatch between when a model should use a tool and when it actually does. The authors decompose tool use into cognition and action stages, finding that the majority of errors occur in translating recognition into action, identifying a 'knowing-doing gap' in LLM tool use.