16 Matching Annotations
  1. Mar 2023
  2. Feb 2023
    1. Wordcraft Writers Workshop by Andy Coenen - PAIR, Daphne Ippolito - Brain Research Ann Yuan - PAIR, Sehmon Burnam - Magenta

      cross reference: ChatGPT

    2. A recurring theme in the authors’ feedback was that Wordcraft could not stick to a single narrative arc or writing direction.
    3. Several participants noted the occasionally surreal quality of Wordcraft's suggestions.

      Wordcraft's hallucinations can create interesting and creatively surreal suggestions.

      How might one dial up or down the ability to hallucinate or create surrealism within an artificial intelligence used for thinking, writing, etc.?

    4. Wordcraft tended to produce only average writing.

      How to improve on this state of the art?

    5. language models are incredible "yes, and" machines, allowing writers to quickly explore seemingly unlimited variations on their ideas.
    6. Wordcraft shined the most as a brainstorming partner and source of inspiration. Writers found it particularly useful for coming up with novel ideas and elaborating on them. AI-powered creative tools seem particularly well suited to sparking creativity and addressing the dreaded writer's block.

      Just as using a text for writing generative annotations (having a conversation with a text) is a useful exercise for writers and thinkers, creative writers can stand to have similar textual creativity prompts.

      Compare Wordcraft affordances with tools like Nabokov's card index (zettelkasten) method, Twyla Tharp's boxes, MadLibs, cadavre exquis, et al.

      The key is to have some sort of creativity catalyst so that one isn't working in a vacuum or facing the dreaded blank page.

    7. The workshop cohort consisted of 13 professional writers, who were given 8 weeks to use Wordcraft. Unlike more constrained user studies run in the past, we gave writers freedom to write anything they wanted using any workflow they could devise. We share below some of the insights we learned through this process.

      How much training did they get with the tool prior to use, particularly those without any experience?

    8. In addition to specific operations such as rewriting, there are also controls for elaboration and continutation. The user can even ask Wordcraft to perform arbitrary tasks, such as "describe the gold earring" or "tell me why the dog was trying to climb the tree", a control we call freeform prompting. And, because sometimes knowing what to ask is the hardest part, the user can ask Wordcraft to generate these freeform prompts and then use them to generate text. We've also integrated a chatbot feature into the app to enable unstructured conversation about the story being written. This way, Wordcraft becomes both an editor and creative partner for the writer, opening up new and exciting creative workflows.

      The interface of Wordcraft sounds like some of that interface that note takers and thinkers in the tools for thought space would appreciate in their

      Rather than pairing it with artificial intelligence and prompts for specific writing tasks, one might pair tools for though interfaces with specific thinking tasks related to elaboration and continuation. Examples of these might be gleaned from lists like Project Zero's thinking routines: https://pz.harvard.edu/thinking-routines

    9. For instance, if the user selects a phrase, a button to "Rewrite this phrase" is revealed along with a text input in which the user can describe how they would like the phrase to be rewritten. The user might type "to be funnier" or "to be more melancholy", and the Wordcraft application uses LaMDA and in-context learning to perform the task.
    10. We like to describe Wordcraft as a "magic text editor". It's a familiar web-based word processor, but under the hood it has a number of LaMDA-powered writing features that reveal themselves depending on the user's activity.

      The engineers behind Wordcraft refer to it "as a 'magic text editor'". This is a cop-out for many versus a more concrete description of what is actually happening under the hood of the machine.

      It's also similar, thought subtly different to the idea of the "magic of note taking" by which writers are taking about ideas of emergent creativity and combinatorial creativity which occur in that space.

    11. The application is powered by LaMDA, one of the latest generation of large language models. At its core, LaMDA is a simple machine — it's trained to predict the most likely next word given a textual prompt. But because the model is so large and has been trained on a massive amount of text, it's able to learn higher-level concepts.

      Is LaMDA really able to "learn higher-level concepts" or is it just a large, straight-forward information theoretic-based prediction engine?

    12. Our team at Google Research built Wordcraft, an AI-powered text editor centered on story writing, to see how far we could push the limits of this technology.
    1. First, I’m impressed as hell by the Wordcraft team. Daphne Ippolito, Ann Yuan, Andy Coenen, Sehmon Burnam, and their colleagues engi­neered an impres­sive, provoca­tive writing tool, but/and, more importantly, they inves­ti­gated its use with sensi­tivity and courage.