Writing complete stories is considered a hallmark display of human intelligence, and thus researchers in artificial intelligence (AI) and natural language generation (NLG) have long used it as a pinnacle task for their research (Klein et al., 1973; Meehan, 1977; Turner, 1993; Dehn, 1981; Liu and Singh, 2002; McIntyre and Lapata, 2009). Creative writing and storytelling present unique challenges for automatic language generation: story arcs extend over thousands of words, stories typically contain multiple characters with their own distinctive personas and voices, and well-written stories have an authorial voice that is consistent and identifiable. At the same time, lies and fabrications-common generation flaws which are a liability in tasks like machine translation and automatic summarization-can be an asset in the creative domain. In recent years, the field of NLG has progressed by leaps and bounds due to the development of neural language models capable of learning the structure of language by ingesting billions of written words (Chowdhery et al., 2022; Zhang et al., 2022; Brown et al., 2020). There has been considerable work in applying these advancements toward the development of AI-powered tools for creative writing, but nearly all previous research in this space has evaluated their methods either with amateur writers or with crowd workers paid to assess performance on narrowly defined tasks (Clark et al., 2018; Roemmele and Gordon, 2015; Nichols et al., 2020). While these sorts of evaluations are valuable as preliminary assessments, we believe it is also crucial to solicit feedback from actual domain experts in creative writing: professional writers, educators, and language experts. Skilled writers comprise a unique user group with a different set of needs and expectations than amateurs.

Amidst the rapid emergence of new AI writing tools and the consolidation of old ones, Google has been testing its own: Wordcraft. The company brought together a group of professional authors to try out the tool in a project called the Wordcraft Writers Workshop--and the results are impressive. Wordcraft, which went under the radar for half a year, was originally released in March. Based on LaMDA--the non-sentient language model that went viral over a conversation on AI consciousness--Wordcraft is presumably more capable than any GPT-3-based tool out there (that is, practically all tools out there). This innovative workshop was unveiled in this year's AI@ event in which the company shares the latest news on AI research.

Artificial intelligence has come a long way since the 1950s, and it has taken on an impressive array of tasks. It can solve math problems, detect natural disasters, identify different living organisms, pilot ships and more. But for tech giants like Google and Meta, one of their holy grails is formulating an AI that can understand language the way that humans do (a quest that at times, comes with its own set of conflicts). A key test for language models is writing--an exercise that many people struggle with as well. Google engineers designed a proof-of-concept experiment called Wordcraft that used its language model LaMDA to write fiction.

Neural language models are gaining popularity in real-life creative tasks such as text-adventure games, collaborative slogan writing, and even sports journalism, poetry and novel generation. Most such language models however provide limited interaction support for users, as control that goes beyond simple left-to-right text generation requires explicit training. To address this limitation, a team from Google Research has proposed Wordcraft, a text editor with a built-in AI-powered creative writing assistant. Wordcraft leverages few-shot learning and the natural affordances of conversation to support a variety of user interactions; and can help with story planning, writing and editing. The Wordcraft web interface comprises a traditional text editor augmented with a number of key commands for triggering requests to the AI assistant.

In a paper accepted to last week's International Conference on Machine Learning, researchers at University College London and the University of Oxford propose an environment -- WordCraft -- to benchmark AI agents' commonsense reasoning capabilities. Based on Little Alchemy 2, a game that tasks players with mixing ingredients to create new items, they say WordCraft is both lightweight and built upon entities and relations inspired by real-world semantics. As the researchers note, personal assistants and household robots require agents that can learn quickly and generalize well to novel situations. That's likely not possible without the ability to reason using common sense and general knowledge about the world. For instance, an agent tasked with performing common household chores that hasn't seen a dirty ashtray would need to know a reasonable set of actions, including how to clean the ashtray and to avoid feeding it to a pet.

The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpora and integrate it with reinforcement learning (RL) agents remains an open challenge. This is partly due to the lack of lightweight simulation environments that sufficiently reflect the semantics of the real world and provide knowledge sources grounded with respect to observations in an RL environment. To better enable research on agents making use of commonsense knowledge, we propose WordCraft, an RL environment based on Little Alchemy 2. This lightweight environment is fast to run and built upon entities and relations inspired by real-world semantics. We evaluate several representation learning methods on this new benchmark and propose a new method for integrating knowledge graphs with an RL agent.