Search
559 results for “marcusgreen”
-
@marcusgreen The real problem is #Google, which rapes #Android and the open‑source license, forcing you to use only Google or certified apps, on top of its web monopoly. Institutions and #banks are corrupt and obey the rules imposed by these companies. The problem is our #EU own institutions, which stifle competition by endorsing regulations from these American companies. #Europe
-
@marcusgreen The real problem is #Google, which rapes #Android and the open‑source license, forcing you to use only Google or certified apps, on top of its web monopoly. Institutions and #banks are corrupt and obey the rules imposed by these companies. The problem is our #EU own institutions, which stifle competition by endorsing regulations from these American companies. #Europe
-
@marcusgreen The real problem is #Google, which rapes #Android and the open‑source license, forcing you to use only Google or certified apps, on top of its web monopoly. Institutions and #banks are corrupt and obey the rules imposed by these companies. The problem is our #EU own institutions, which stifle competition by endorsing regulations from these American companies. #Europe
-
@marcusgreen The real problem is #Google, which rapes #Android and the open‑source license, forcing you to use only Google or certified apps, on top of its web monopoly. Institutions and #banks are corrupt and obey the rules imposed by these companies. The problem is our #EU own institutions, which stifle competition by endorsing regulations from these American companies. #Europe
-
@marcusgreen The real problem is #Google, which rapes #Android and the open‑source license, forcing you to use only Google or certified apps, on top of its web monopoly. Institutions and #banks are corrupt and obey the rules imposed by these companies. The problem is our #EU own institutions, which stifle competition by endorsing regulations from these American companies. #Europe
-
I gave a presentation at #MoodleMootEstonia26 today on the subject of AI Feedback on low stakes assessment. I described the AI Text Question Type and the AIF feedback plugin for the #Moodle assignment module.
-
It looks like #curve does a KYC check for UK only.
I'm in Oz, but I will go through the whole dance, as it's the only way right now (if it works)
Thanks! -
#Deepwiki uses an #LLM to create wiki pages for #Github repositories. You can see an example here for the #Moodle Assignment AIF plugin which uses an external LLM #AI System to give feedback on assignment submissions. It will will factor in any #Rubric associated with the assignment. It now needs a nice logo.
-
AI Chat block customised for #STACK
I have created a video demonstrating the #Moodle AI Chat block from #ByCS with “agent mode”.
It adds “context” along with the user's question in the form of the strings in with the current form. In addition it can have page specific context. In the video I have added the context from
https://github.com/marcusgreen/moodle-block_ai_chat/blob/main/docs/qtype_stack_context.md
If you would like to experiment with this using a teacher account email me at
[email protected]
https://www.youtube.com/watch?v=VVW8m9lXTsk -
I have updated my wiki documentation on Moodle #LLM Back ends. This is mainly about my #aitext question type, but it is applicable to anyone working on #Moodle #AI plugins.
https://github.com/marcusgreen/moodle-qtype_aitext/wiki/Selecting-a-Back-End
-
The next release of my AI Text question type is ready to be published to the #Moodle plugins databse. You can read the release notes here
https://github.com/marcusgreen/moodle-qtype_aitext/blob/main/changelog.md
#AIText uses an external #LLM to evaluate student responses.
You can see the roadmap here
https://github.com/marcusgreen/moodle-qtype_aitext/wiki/Roadmap -
@marcusgreen Ahhh, do like a bit of old-skool #EdPsy #CogSci!
Craik, F. I. M., & Lockhart, R. S. (1972). Levels of processing: A framework for memory research. Journal of Verbal Learning and Verbal Behavior, 11(6), 671–684. https://doi.org/10.1016/S0022-5371(72)80001-X
Morris, C. D., Bransford, J. D., & Franks, J. J. (1977). Levels of processing versus transfer appropriate processing. Journal of Verbal Learning and Verbal Behavior, 16(5), 519–533. https://doi.org/10.1016/S0022-5371(77)80016-9
-
@marcusgreen Ahhh, do like a bit of old-skool #EdPsy #CogSci!
Craik, F. I. M., & Lockhart, R. S. (1972). Levels of processing: A framework for memory research. Journal of Verbal Learning and Verbal Behavior, 11(6), 671–684. https://doi.org/10.1016/S0022-5371(72)80001-X
Morris, C. D., Bransford, J. D., & Franks, J. J. (1977). Levels of processing versus transfer appropriate processing. Journal of Verbal Learning and Verbal Behavior, 16(5), 519–533. https://doi.org/10.1016/S0022-5371(77)80016-9
-
@marcusgreen Ahhh, do like a bit of old-skool #EdPsy #CogSci!
Craik, F. I. M., & Lockhart, R. S. (1972). Levels of processing: A framework for memory research. Journal of Verbal Learning and Verbal Behavior, 11(6), 671–684. https://doi.org/10.1016/S0022-5371(72)80001-X
Morris, C. D., Bransford, J. D., & Franks, J. J. (1977). Levels of processing versus transfer appropriate processing. Journal of Verbal Learning and Verbal Behavior, 16(5), 519–533. https://doi.org/10.1016/S0022-5371(77)80016-9
-
@marcusgreen Ahhh, do like a bit of old-skool #EdPsy #CogSci!
Craik, F. I. M., & Lockhart, R. S. (1972). Levels of processing: A framework for memory research. Journal of Verbal Learning and Verbal Behavior, 11(6), 671–684. https://doi.org/10.1016/S0022-5371(72)80001-X
Morris, C. D., Bransford, J. D., & Franks, J. J. (1977). Levels of processing versus transfer appropriate processing. Journal of Verbal Learning and Verbal Behavior, 16(5), 519–533. https://doi.org/10.1016/S0022-5371(77)80016-9
-
@marcusgreen Ahhh, do like a bit of old-skool #EdPsy #CogSci!
Craik, F. I. M., & Lockhart, R. S. (1972). Levels of processing: A framework for memory research. Journal of Verbal Learning and Verbal Behavior, 11(6), 671–684. https://doi.org/10.1016/S0022-5371(72)80001-X
Morris, C. D., Bransford, J. D., & Franks, J. J. (1977). Levels of processing versus transfer appropriate processing. Journal of Verbal Learning and Verbal Behavior, 16(5), 519–533. https://doi.org/10.1016/S0022-5371(77)80016-9
-
AI Tag Suggestions
My #Moodle #qbank #bulktags plugin allows the quick update of multiple questions with the same tag. There is a Moodle 5.0 compatible branch that has a setting for #AI #LLM suggestions based on the question text. It will work with either the core AI subsystem or Local ai_manager from ByCS Learn Platform.
Read more about bulktags AI Suggestions here
https://github.com/marcusgreen/moodle-qbank_bulktags/wiki/AI-Suggestions
-
There is an issue in my #Moodle #bulktags plugin where it doesn't work with Moodle 4.5. There was a change in function signature between 4.5 and 5.
There is a full description here
https://github.com/marcusgreen/moodle-qbank_bulktags/issues/1
which points to a branch that should fix the issue. I would appreciate feedback to confirm that branch works as expected. I cannot think of a way to fix it apart from haivng two different branches....
-
It is always a pleasure to get a well asked question on one of my #Moodle plugins. This question was about my #AIText question type which uses an external #AI #LLM to generate feedback on students free text responses. On a side note I have found #Google #Gemini works at least as well or better than #OpenAI #ChatGPT models.
It was an issue I had not documented until now and as many people use it for language learning, it matters.
https://github.com/marcusgreen/moodle-qtype_aitext/issues/32
-
I have been thinking about how to allow more flexible prompting for my #Moodle #AIText question type. At the moment the prompt entered into the editing form is “wrapped”, which limits what a question author can do. I have created a github wiki page that proposes a “raw” mode to allow full flexibility for more experienced developers.
You can see the description here
https://github.com/marcusgreen/moodle-qtype_aitext/wiki/Raw-prompt-mode
Feedback appreciated
#EdTech #Education #AI #LLM -
My #AIText #Moodle question type uses an external AI/LLm to evaluate student responses. I have developed a branch which allows the creation of multiple test responses for use when editing a question. You can see the branch and test it out at
https://github.com/marcusgreen/moodle-qtype_aitext/tree/response_testIt is beta code but I am fairly confident it works as expects and I intend merging it into the main branch in the near future. Feedback would be apprciated
-
-
All software has #bugs
I made my first github commit for the #Moodle #Gapfill question type In April 2012. I have made 1,510 commits since then. This year on Feb 5 2025 Mark Johnson reported a bug in backup caused by spelling errors in field names.
https://github.com/marcusgreen/moodle-qtype_gapfill/issues/117
I have created a #behat test to reproduce the bug and a patch to fix it. It took approximately 5 hours in total.
All software has bugs, automated tests are not a luxury. -
I have been downloading Large Language Models for testing with #ollama and #openwebui I am evaluating them specifically for my #Moodle #AIText question type, which is available under the #GPL from
https://github.com/marcusgreen/moodle-qtype_aitext
You can experiment with it here
https://examulator.com/cg/
I want to see how they deal with #translation and language evaluation. The question type is popular with #TEFL, or teaching english as a foreign language -
@marcusgreen C4L also has a version for TinyMCE - we chose it as one part of our plugin set to make the amazing work of @FrauSpeckner available in an easy way to our teachers. At #MoodleMootDACH in Vienna we started (and finished a first working version) our work on a fork of tiny_c4l to allow configuring the components/categories/... via admin backend (with the upstream version you need to change JS and SCSS in the plugin to do that), to make it a bit more flexible and ready for sharing designs
-
I was updating the readme file for my #Moodle question bank #bulktags plugin with an #ai assistant enabled (#Cody).
https://github.com/marcusgreen/moodle-qbank_bulktags
I was pleased to see it makes suggestions not just for code but for general text as seen in the attached screenshot.Having said that it offered an incorrect suggestion that required an understanding of how tags vs categories work.
-
Bulk tag #Moodle #quiz questions
AT #MootDach 24 I spent a little time with the very talented Stephan Robotta on the Question Bank XML export.
https://github.com/bfh/moodle-qbank_bulkxmlexport
Inspired by that, I then worked on my #Question Bank Bulk #Tags plugin. Like the core bulk move functionality you can select multiple questions and then add the same tag to all those questions. You can either replace the existing tags, or add to them. You can find the code in beta form at https://github.com/marcusgreen/moodle-qbank_bulktags
-
Bulk tag #Moodle #quiz questions
AT #MootDach 24 I spent a little time with the very talented Stephan Robotta on the Question Bank XML export.
https://github.com/bfh/moodle-qbank_bulkxmlexport
Inspired by that, I then worked on my #Question Bank Bulk #Tags plugin. Like the core bulk move functionality you can select multiple questions and then add the same tag to all those questions. You can either replace the existing tags, or add to them. You can find the code in beta form at https://github.com/marcusgreen/moodle-qbank_bulktags