4 entries
Annotation of So, Cheng & Krishna Murthy (2026). CHI EA '26. Proposes a spectrum of LLM interface metaphors from anti- to hyper-anthropomorphism to encourage critical engagement.
Treats prompts as first-class delivery artefacts: version-controlled, reviewed, and refined alongside code. Introduces the REASONS Canvas — a seven-part template covering requirements, entities, approach, structure, operations, norms, and safeguards — and a six-step workflow that fixes the prompt before fixing the code when reality diverges.
Microsoft researchers introduce DELEGATE-52, a benchmark of long document-editing workflows across 52 professional domains. Even frontier models (Gemini 3.1 Pro, Claude 4.6 Opus, GPT-5.4) corrupt about 25% of document content by the end of these workflows, and agentic tool use does not improve performance. The paper argues current LLMs are unreliable delegates: they introduce sparse but severe errors that compound silently over long interactions.
Argues that the mental model you bring to AI determines how effectively you work with it. Catalogues thirteen metaphors (bionic mind, smart intern, word calculator, genie, sparring partner, and others), each surfacing different affordances and risks of LLMs. The framing is operational: pick the metaphor that fits the task, switch deliberately, avoid being trapped by one.