5 Matching Annotations
  1. Last 7 days
    1. When using a model separately from an agent, it is up to you to execute the requested tool and return the result back to the model for use in subsequent reasoning.

      Model Suggestion: The LLM's initial call returns an AIMessage containing the suggestion to use a specific tool (the tool_calls object).

      Developer Action (Execution): The developer's code must intercept this message, parse the tool name and arguments, and manually execute the corresponding Python function.

      Result Feedback: The developer must then package the output of the tool execution into a ToolMessage and send it back to the Model, along with the previous conversation history, for the Model to complete its final reasoning and generate the answer.

  2. Nov 2023
    1. Do digital note taking tools extend the ranges of affordances versus their analog counterparts with respect to the SAMR model?

      On the augmentation front, they allow one to capture things faster, but may do so at the loss of understanding due to the lack of active learning (versus passive as the tool may be robbing them of the interaction with the material).

      There may be some workflow modification, but it's modest at best. Is it measurably better?

      I'm unaware of anyone talking about technological redefinition of digital note taking affordances, though some of the surface level AI-related things may emerge here.

      In some sense, I still think that the ease of remapping and rearranging/linking/relinking/outlining ideas in digital spaces doesn't exist, so digital note taking tools aren't doing very well even at the root substitution level.

      I suspect that some people weren't exposed to the general process of good note taking and their subsequent use for linking, developing, and then creating and as a result of learning this, they're attributing their advances to the digital nature of their tools rather than the original analog process which was always there and isn't necessarily improved measurably by the digital modality.

  3. Jan 2023
    1. 个人学习可能取决于他人行为的主张突出了将学习环境视为一个涉及多个互动参与者的系统的重要性
  4. Nov 2022
    1. Donations

      To add some other intermediary services:

      To add a service for groups:

      To add a service that enables fans to support the creators directly and anonymously via microdonations or small donations by pre-charging their Coil account to spend on content streaming or tipping the creators' wallets via a layer containing JS script following the Interledger Protocol proposed to W3C:

      If you want to know more, head to Web Monetization or Community or Explainer

      Disclaimer: I am a recipient of a grant from the Interledger Foundation, so there would be a Conflict of Interest if I edited directly. Plus, sharing on Hypothesis allows other users to chime in.