19 Matching Annotations
  1. Aug 2024
    1. Stripped out all the legacy "desktop UI" stuff, and replaced with a simpler "multi-page notebook" metaphor, then it could be massively more compelling to people. It then becomes a "personal notebook" for doing little sketches / experiments.If it's also "social" ie. has chat streams. Or is like the Smallest Federated Wiki. Or has other ways to sync sketches and pages etc. then this would be spectacular.And the Smalltalk VM / infrastructure is perfect for it.

      I have found the GT/Lepiter GUI pretty compelling for learners in my local hackerspace and in the information science department, both spaces where I'm a facilitator/teacher. It provides a pretty focused experience and it is stripped down of the overwhelming initial experience of the Pharo/Squeak GUI. It is not well suited for "classical Smalltalkers" though. as I have been talking with some of them and they find the DX too much specific and even cumbersome for some task they usually do (it has been not our case so far).

      In our last use case at the university, the students are creating a personal code repository in Fossil, with data narratives and they do a critic/annotated reading, using Hypothesis (this very technology), which is kind of a personal public wiki-like portfolio for data narratives. They put also the reading notes in their own repositories for the data stories I published previously where I introduce Smalltalk or and introduction to data representation and processing in Pharo.

      This could be another approach for wikis in the classroom, that is alterative to our use of interpersonal wikis with TiddlyWiki. At some point and in a pretty organic way, the idea would be to have all them integrated and powered by "context aware" and thematic chatbots (made in Pharo).

  2. Jul 2024
  3. Oct 2023
  4. Sep 2023
  5. Feb 2023
    1. 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

  6. Dec 2022
    1. At the abstract level of empirical investigation concerned with the theory of science is communication with slip boxes certainly only one of many possibilities. The accidents of reading play a role just as much as misunderstandings resulting from interdisciplinary thought processes. We can confirm hat communication with slip boxes may be considered as a functional equivalent and that this approach, compared to others, has many advantages as far as speed, and mutual adaptability is concerned.

      Otras posibilidades son chatbots y wikis, entre las variantes descritas acá, dentro de las muchas posibles y por explorar.

    2. Naturally, independence presupposes a minimal measure of intrinsic complexity. The slip box needs a number of years in order to reach critical mass. Until then, it functions as a mere container from which we can retrieve what we put in. This changes with its growth in size and complexity. On the one hand, the number of approaches and occasions for questions increases. The slip box becomes a universal instrument. You can place almost everything in it, and this not just ad hoc and in isolation, but with internal possibilities of connections [with other contents]. It becomes a sensitive system that internally reacts to many ideas, as long as they can be noted down. If we ask, for instance, why on the one hand museums are empty, while on the other hand exhibitions of paintings by Monet, Picasso, or Medici are too crowded, the slip box accepts this question under the perspective of “preference for what is temporally limited.”

      Un sistema de preguntas y emergencias similares se puede hacer cuando el slipbox tiene otras materialidades. En mi caso, suelo enviarme mensajes de texto/voz a mí mismo (principalmente vía Telegram), con la esperanza futura de que las pueda tenerlas con un chatbot (en otra red) y que mi yo futuro implementará esas conversaciones algorítmicas, las interconexiones con otros ecosistemas digitales y humanos y las transiciones hacia ellas.

    3. If you wish to educate a partner in communication, it will be good to provide him with independence from the beginning. A slip box, which has been made according to the suggestions just given can exhibit great independence. There may be equally apt ways to reach this goal. The described reduction to a fixed, but merely formal order of placement and the resulting combination of order and disorder is, however, one of these ways.

      Otra de las posibilidades para dar autonomía a ese compañero de comunicación es a través de agencia algorítimica progresiva. A comienzos del milenio proponía un chatbot conectado a chats comunitarios (tipo IRC, en aquella época algo que hoy muestra ChatGPT) y ahora sería chatbots conectados con microwikis.

  7. Jul 2021
  8. Jun 2021
  9. Jun 2020
  10. Nov 2019
    1. However, PIPA is the agency's first standalone bot, meaning it can be used across multiple government agencies. Crucially, the bot can be embedded within web and mobile apps, as well as within third-party personal assistants, such as Google Home and Alexa.  According to Keenan, the gang of five digital assistants released so far by the DHS have answered "more than 2.3 million questions, reducing the need for people to have to pick up a phone or come into a service centre for help.” “This is what our digital transformation program is all about – making life simpler and easier for all Australians.”

      Scope of PIPA

    1. uman Services has a number of public-facing chatbots already. The newest of them is ‘Charles’, launched last year, which offers support for the government’s MyGov service.Others include ‘Sam’ and ‘Oliver’, both of which launched in 2017. The department’s customer-facing digital assistants have so far answered more than 2.3 million questions. Human Services also uses a number of staff-facing chatbots. In November Keenan revealed that the department had launched an Augmented Intelligence Centre of Excellence, which the minister said would boost collaboration with industry, academia and other government entities.

      Chatbots that exist

    1. The federal government has decided that all Commonwealth entities would benefit from having a chatbot, with the Department of Human Services (DHS) announcing it was working on the development of one that will be ready by the end of 2019.The Platform Independent Personal Assistant -- PIPA -- is expected to "significantly improve the customer experience for users of online government services", according to Minister for Human Services and Digital Transformation Michael Keenan.

      Federal Government creating PIPA chatbot

    1. Before implementing Alex 2.5 years ago, IP Australia staffers were taking 12,000 calls per month."Now I'm not saying Alex was the only intervention we had, but it was one of the main ones. Acting on the insights we were getting from Alex, we're now down to 5,000 calls per month and still dropping," Stokes said. "The value for money and return on investment is quite good."

      IP Australia using chatbox named Alex to reduce calls received

  11. Oct 2019
    1. No matter how well you design a system, humans will end up surprising you with how they use it. “We make it obvious that it’s a bot, a digital assistant, at the start. But sometimes customers overlook that. And they’ll say, ‘are you a bot? What’s going on here? Transfer me through!’ And they’ll get into it quite strongly,” explains David Grilli, AGL’s chatbot product owner

      Interesting to note response to chatbots