We consider the problem of automatically generating longer stories of over two thousand words. Compared to prior work on shorter stories, long-range plot coherence and relevance are more central challenges here. We propose the Recursive Reprompting and Revision framework (Re3) to address these challenges by (a) prompting a general-purpose language model to construct a structured overarching plan, and (b) generating story passages by repeatedly injecting contextual information from both the plan and current story state into a language model prompt. We then revise by (c) reranking different continuations for plot coherence and premise relevance, and finally (d) editing the best continuation for factual consistency. Compared to similar-length stories generated directly from the same base model, human evaluators judged substantially more of Re3's stories as having a coherent overarching plot (by 14% absolute increase), and relevant to the given initial premise (by 20%).

Guide dogs help to provide people with vision loss with independence, safety, and, perhaps equally important – companionship. I volunteer as a puppy raiser for Guiding Eyes for the Blind because I saw first-hand how my late husband's vision loss affected him during his battle with cancer. I want to help make lives better for people who are blind or have impaired vision. IBM's Lorraine Trapani holds TJ. (Photo: Darryl J Bautista/Feature Photo Service) Guiding Eyes for the Blind is a non-profit organization dedicated to the breeding, raising, training and placement of guide dogs with people who are blind or visually impaired. Guiding Eyes is using Watson to help pair more guide dogs with those who need them. The stakes are high: each dog costs Guiding Eyes approximately $50,000 to train over two years, and only half of the dogs raised and trained will graduate as guide dogs or be chosen as dogs to breed.

A common difficulty in diagnosing failures within Pratt & Whitney's F100-PW-100/200 gas turbine engine occurs when a fault in one part of a system -- comprising an engine, an airframe, a test cell, and automated ground engine test set (AGETS) equipment -- is manifested as an out-of-bound parameter elsewhere in the system. In such cases, the normal procedure is to run AGETS self-diagnostics on the abnormal parameter. However, because the self-diagnostics only test the specified local parameter, it will pass, leaving only the operators' experience and traditional fault-isolation manuals to locate the source of the problem in another part of the system. This article describes a diagnostic tool (that is, AGETS MBR), designed to overcome this problem by isolating failures using an overall system troubleshooting approach. AGETS MBR was developed jointly by personnel at Pratt & Whitney and United Technologies Research Center using an AI tool called the qualitative reasoning system (QRS).

The acquisition of expert knowledge is fundamental to the certain of expert systems. The conventional approach to building expert systems assumes that the knowledge exists, and that it is feasible to find an expert who has the knowledge and can articulate it in collaboration with a knowledge engineer. This article considers the practice of knowledge engineering when these assumptions can not be strictly justified. It draws on our experiences in the design of VLSI design methods, and in the prototyping of an expert assistant for VLSI design. We suggest methods for expanding the practice of knowledge engineering when applied to fields that are fragmented and undergoing rapid evolution. We outline how the expanded practice can shape and accelerate the process of knowledge generation and refinement. Our examples also clarify some of the unarticulated present practice of knowledge engineering.