Mastodawn

Chatbots vs inline automation and their respective implications for students

In Generative AI for Academics I drew the distinction between conversational agents and templated responses. In the former you interact in natural language with a chatbot through a dialogue, whereas in the latter you select buttons to enact pre-defined transformations to text. This is how I talked about it in a webinar a couple of years ago:

https://youtu.be/GTjd9eLd9cw?si=bGt1KVk2CXKVpQv1&t=2859

Kim et al draw a similar distinction: “Two interaction techniques currently dominate: dialogue (e.g., OpenAI’s ChatGPT and Google’s Gemini) and predictive text completion (e.g., GitHub Copilot)”. I’d suggest that inline automation as found in Microsoft Copilot 365 or Gemini in Google Docs is a development of predictive text completion, in the sense that a user can complete a transformation of text by pushing a button. In both cases the system produces content with the difference being how this production happens: with chatbots it happens through dialogue and with inline automation it happens through pressing a button. If you’re a confident writer who uses chatbots in a purely dialogical way, it’s easy to forget how much chatbot use can be geared towards the production of content. I’d say it’s better educationally in the sense that some articulation is necessary to produce anything from a chatbot. But it’s still outsourcing a task to the machine in a radical way.

The approach developed by Kim et al tries for a third approach which “motivates users to reflect on their text with LLM-generated summaries, questions, and advice on writing (which we refer to as LLM views), helping them discover opportunities for improvement or elaboration”. They offer a useful definition of two stages involved in this process (my emphasis):

Revision means critically examining and evaluating, which we refer to as reflection, and identifying any opportunities for improvement or further development, which we refer to as discovery, and then making the appropriate changes. This can occur at any stage of the writing journey

https://hai-gen.github.io/2024/papers/9904-Kim.pdf

The purpose of their interface is to offer perspectives on the text which scaffold reflection and discovery while avoiding the language model merely producing text directly for the user. They identified three outgrowths in their pilot of the project which are educationally relevant: (1) discovering underdeveloped ideas, (2) catering to their audience, and (3) identifying opportunities to improve clarity.

If we’re going to be using inline automation with students, this suggests how we can do it in a pedagogically responsible way. The purpose is to offer perspectives, taking advantage of how the model is embedded in the office software, rather than predictive text completion. Copilot offers these perspectives which present themselves for educational use. The problem is that (1) they are integrated seamlessly into an interface which is built around inline automation (2) they are not fine tuned for the specific domain so their advice can often be questionable.

But they are nonetheless there, which offers pedagogical opportunities. The key I think is to encourage students to gravitate towards dialogue (using the prompt windows where they are available) and perspectives (using the reflection tools built in) while discouraging them from using the push-button forms of automation. Where these are used, they need to be engaged with thoughtfully: to reflect on why you are selecting this button and to review the consequences of pressing it. The challenge is introducing moments of friction and reflection into software which is fundamentally designed to be frictionless, but it’s not insurmountable I think. Engaging with it educationally in this way though presupposes a lot of critical AI literacy in general and familiarity with Copilot 365 in particular.

#conversationalAgents #copilot #inlineAutomation #metacognition #pedagogy #reflection #teaching

How is AI changing the teaching and academic landscape?

YouTube

YOOTA Apr 14

Shopify Opens AI Agent Toolkit for Developers

Shopify launches its AI Toolkit for developers, enabling direct integration with AI agents like Cursor and Claude. Here's what changes for e-commerce and app builders.

https://yoota.it/en/shopify-opens-ai-agent-toolkit-for-developers/

AI Daily Post Mar 1

Regulators are zeroing in on AI deepfakes, but the quieter threat lives in everyday chatbots, wearables, and subtle algorithmic nudges. How will Meta, Google and others shape the rules? Dive into the hidden risks shaping our digital lives. #AIDeepfakes #ConversationalAgents #AlgorithmicPersuasion #TechRegulation

🔗 https://aidailypost.com/news/regulators-focus-ai-deepfakes-while-everyday-whispers-pose-unseen-risk

Agent_Asof Jan 27

What if agents could not just respond, but truly understand over long conversations? 🌟 LUMINA is paving the way for multi-turn interactions by giving AI the ability to remember context and engage more naturally! This could transform how we interact with AI, making it more intuitive and useful. Imagine a future where your digital assistants can hold meaningful dialogues! Dive into the implications of this tech and discover why it matters. #AI #ConversationalAgents

Viktoria Pammer-Schindler Nov 5, 2025

#postdoc #hiring - I have a 1-year opening, to be started early next year, for a postdoc in #hci and #edtech in the E+ project L2BGreen. The ideal candidate will be interested in investigating interaction design patterns for #conversationalAgents, especially mixing textual/visual/voice-based communication. Contact me for questions, applications must be via the job portal: https://lnkd.in/dmAa_nAa

This link will take you to a page that’s not on LinkedIn

nolan at KillBait Oct 18, 2025

Evaluating the Impact of AI Conversational Agents on Patient Experience with Physicians in Chinese Outpatient Services

This study investigates how artificial intelligence-assisted conversational agents (chatbots) affect patient experience during outpatient visits in tertiary public hospitals in China. Using the Chinese Outpatient Experience Questionnaire, researchers surveyed 394 adult residents from various regions... [More info]

Chris J. Karr Sep 25, 2025

Proud to be part of the @jonahjmeyerhoff.bsky.social's team making this system a reality! #ConversationalAgents #SuicidePrevention #TextMessaging #MentalHealth

RE: https://bsky.app/profile/did:plc:xgggn77siqk5xtoiet4xknaj/post/3lzjj5ipy4s2h

Mark Carrigan May 11, 2025

How Claude is changing: five observations about Sonnet 3.7

There’s not really much point in defining a role for the LLM any more. Whenever I use role definitions which were effective in previous models, I now find myself getting frustrated by its rigidity relative to how the base model behaves without starting guidance. In my experience it’s become startlingly effective at inferring the kind of conversation you’re inclined to have, even if you’re not entirely sure what that is at the outset, without prior guidance.

It’s increasingly adept at asking thought-provoking questions which can help steer the direction of this conversation, with particularly significant results when you are yourself uncertain about what the purpose of the conversation should be. I used to ignore LLM questions as a matter of reflex, regarding them as discursive forth, but I’m increasingly inclined to think about the questions Claude 3.7 asks for intrinsic value and because they guide the ensuing conversation.

If you want to have a specialised conversation in which you work with complex ideas then it can help to have a general dialogue about these ideas before you try and push it in a certain direction. In effect I’m finding that you can ‘warm up’ the model and it becomes a more effective interlocutor (to talk about, say, Lacanian psychoanalysis or talk through the political economy of LLMs) then if you just dive straight into the initial conversation.

In effect I think this means you now have to steer the model in the direction you want to go in, in terms of the domain, rather than define a role for it. The risk is that if you don’t do this, you will be steered by the model, which can make their use more accessible but significantly erodes the agency which can be exercised in relation to them. The inclination Claude has had since Opus to infer a domain from specialised vocabulary seems to increased substantially. For example if you want to have a conversation about social ontology with it, the best thing is to simply start talking to it about social ontology (at the level you would in an academic article) before introducing the practical concerns driving the conversation.

I worry that the existing tendency for divergent experiences depending on cultural capital (the range of symbols available to you, the fluency with which you articulate them etc) in which Claude 3.7 can literally do things for users who can write a lot in a specialised way which it can’t for users who lack these characteristics. For academics it means my core advice from Generative AI for Academics holds even more than it did a year ago i.e. just start talking to the LLM in the way you would a collaborator about your work. But I’m not sure what this means for less specialised users and this concerns me.

#claude #conversation #conversationalAgents #dialogue #prompting