Doug Holton

@dougholton
1.9K Followers
1.4K Following
2.2K Posts
Learning physics can derail some students: New research shows the best way to keep them on track https://phys.org/news/2026-05-physics-derail-students-track.html
Summary of: Relative benefits of different active learning methods to conceptual physics learning https://www.nature.com/articles/s41567-026-03307-2
#PhysicsEd #STEMeducation #ActiveLearning #Teaching
Learning physics can derail some students: New research shows the best way to keep them on track

For many undergraduate students, exploring the complexities of physics for the first time, from wading through advanced mathematics, to absorbing information in a large lecture format, can be a daunting endeavor—one that dissuades many students from continuing their studies.

Phys.org

ffmpeg webCLI: browser-based video editor.

No uploads, no servers -- all processing happens locally in your browser using #WebAssembly. Looks COOL. 😮

GIF creation, format conversion, compression, trimming, effects, filters, etc.

#video #webdev #JavaSCript

https://github.com/tejaswigowda/ffmpeg-webCLI

GitHub - tejaswigowda/ffmpeg-webCLI: A browser-based video editor powered by ffmpeg.wasm. No uploads, no servers -- all processing happens locally in your browser using WebAssembly.

A browser-based video editor powered by ffmpeg.wasm. No uploads, no servers -- all processing happens locally in your browser using WebAssembly. - tejaswigowda/ffmpeg-webCLI

GitHub
One rule I put in my CLAUDE.md for the podcast app: every code change runs through accessibility agents automatically. Thanks to @tayarndt and @JeffBishop for your work on these agents! No exceptions. That's not optional. That's the baseline.
@damashe and I got into why in episode 165 of Technically Working.
https://technicallyworking.show
#TechnicallyWorking #Accessibility #A11y #BlindTech #AssistiveTechnology
Technically Working

"Welcome to 'Technically Working', the go-to podcast for tech enthusiasts and productivity seekers alike. Hosts Michael Babcock and Damashe Thomas take you on a journey through the ever-evolving world of technology and productivity. As Mac OS and iPhone users, they share their personal experiences and tips on staying productive while using these tools. But they don't stop there - they also explore other platforms like Android and Windows to bring you a comprehensive view of the tech landscape. Tune in each episode to hear them keep each other accountable, discuss the latest tools and strategies, and share their journey to reaching their goals. Whether you're a small business owner, freelancer, or simply looking to boost your productivity, 'Technically Working' is the perfect podcast for anyone looking to level up their tech skills and get things done."

New blog post: Using an #OpenCode agent to sort through my #RSS subscriptions of blogs, academic publications, vendor announcements, Github commits, videos and social media posts to get a daily digest of graphics papers that fit my domain and interests.

https://www.tobias-franke.eu/log/2026/05/30/agent-opml.html

Agentic AI Video Motion Graphics and HTML Presentations – Create Multimedia with Free Fast Web Dev Tools and AI

This post describes my recent experiments with #agenticai #vibecoding tools for creating #presentations and #video for #instructionaldesign.

https://tedcurran.net/2026/05/agentic-ai-video-motion-graphics-and-html-presentations-create-multimedia-with-free-fast-web-dev-tools-and-ai/

Agentic AI Video Motion Graphics and HTML Presentations – Create Multimedia with Free Fast Web Dev Tools and AI

This post describes my recent experiments with #agenticai #vibecoding tools for creating #presentations and #video for #instructionaldesign.

Ted Curran.net

"AI assistance impairs independent performance and reduces persistence."

https://arxiv.org/abs/2604.04721

#solidstatelife #ai #genai #llms #psychology #persistence

AI Assistance Reduces Persistence and Hurts Independent Performance

People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks progress, and prioritizes the other person's growth over immediate results. In contrast, current AI systems are fundamentally short-sighted collaborators - optimized for providing instant and complete responses, without ever saying no (unless for safety reasons). What are the consequences of this dynamic? Here, through a series of randomized controlled trials on human-AI interactions (N = 1,222), we provide causal evidence for two key consequences of AI assistance: reduced persistence and impairment of unassisted performance. Across a variety of tasks, including mathematical reasoning and reading comprehension, we find that although AI assistance improves performance in the short-term, people perform significantly worse without AI and are more likely to give up. Notably, these effects emerge after only brief interactions with AI (approximately 10 minutes). These findings are particularly concerning because persistence is foundational to skill acquisition and is one of the strongest predictors of long-term learning. We posit that persistence is reduced because AI conditions people to expect immediate answers, thereby denying them the experience of working through challenges on their own. These results suggest the need for AI model development to prioritize scaffolding long-term competence alongside immediate task completion.

arXiv.org
Single-Session Interventions for Mental Health Problems and Service Engagement: Umbrella Review of Systematic Reviews and Meta-Analyses https://www.annualreviews.org/content/journals/10.1146/annurev-clinpsy-081423-025033
Recent example:
Using a new online mental health tool just once boosts UK teenagers' hope and emotional well-being https://medicalxpress.com/news/2026-04-online-mental-health-tool-boosts.html
Project Action Brings Change (ABC) Tool & related resources: https://unlockwellbeing.org.uk/
#MentalHealth #Psy #Mindset
Single-Session Interventions for Mental Health Problems and Service Engagement: Umbrella Review of Systematic Reviews and Meta-Analyses

Most people with mental health needs cannot access treatment; among those who do, many access services only once. Accordingly, single-session interventions (SSIs) may help bridge the treatment gap. We conducted the first umbrella review synthesizing research on SSIs for mental health problems and service engagement in youth and adults. Our search yielded 24 systematic reviews of SSIs, which included 415 unique trials. Twenty reviews (83.33%) reported significant, positive effects of SSIs for one or more outcomes (anxiety, depression, externalizing problems, eating problems, substance use, treatment engagement or uptake). Across 12 reviews that meta-analytically examined SSIs’ effectiveness relative to controls, SSIs showed a positive effect across outcomes and age groups (standardized mean difference = −0.25, I2 = 43.17%). Per AMSTAR 2 (A Measurement Tool to Assess Systematic Reviews), some methodological concerns emerged across reviews, such as low rates of preregistration. Overall, findings support the clinical utility of SSIs for certain psychological problems and populations. Implementation research is needed to integrate effective SSIs into systems of care.

Annual Reviews
The Goblin Tools suite is designed for neurodivergent folks, but it can be useful for anyone. Here's the simple AI workflow one of our writers used to turn a daunting weekend project list into a series of small wins. https://www.pcmag.com/articles/free-ai-powered-goblin-tools-helped-me-crush-my-household-tasks
Some recent #AIEd articles:
* PromptDecipher: AI Tutor Authoring Through Editable Simulated Interactions https://arxiv.org/abs/2605.16605 Source code: https://anonymous.4open.science/r/teacher-prompting-2EDF/README.md
* Tutoring Agents Struggle Where Feedback Matters Most https://arxiv.org/abs/2605.16207v1
* Modeling AI-TPACK in Practice https://arxiv.org/abs/2605.13906
* Validating AI-Generated Classroom Observations https://www.sciencedirect.com/science/article/pii/S2666920X26000743?dgcid=raven_sd_aip_email
* Simulating Students or Sycophantic Problem Solving? https://arxiv.org/abs/2605.12748
#EdTech
PromptDecipher: Supporting AI Tutor Authoring Through Editable Simulated Interactions

Chatbots have long been explored as tools to support learning, and recent advances in large language models have significantly expanded the availability of platforms for educators to author AI tutoring chatbots. Yet effective authorship demands more than writing a system prompt; it requires educators to act as learning designers, AI interaction designers, and QA engineers. In practice, however, teachers rarely fulfill these roles. Our formative study found that virtually none systematically tested their bots before deploying them to students. To address this gap, we present PromptDecipher, a system that restructures the authoring workflow around a direct correction-based interaction rather than writing abstract system prompts, teachers interact with a live chat preview and edit undesirable bot responses. An automated pipeline then analyzes the correction, proposes a targeted system prompt rewrite, and validates the change across pre-defined test scenarios. This enforces QA as a first-class activity and scaffolds teachers in roles they would otherwise skip. PromptDecipher will be deployed in an AI for Educators course enrolling hundreds of higher-education instructors. A live prototype (https://teacher-prompting.vercel.app/), an anonymized codebase (https://anonymous.4open.science/r/teacher-prompting-2EDF/), and anonymized demo (https://tinyurl.com/las-prompt-decipher-demo) are available via links in the footnote.

arXiv.org