Skip to content

Commit 17c97b5

Browse files
committed
update
1 parent 534f4e2 commit 17c97b5

7 files changed

Lines changed: 104 additions & 2 deletions

File tree

journals/2026_03_30.md

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,4 +3,20 @@
33
- [shareAI-lab/learn-claude-code: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1](https://github.com/shareAI-lab/learn-claude-code)
44
- [ChatGPT acts as a "cognitive crutch" that weakens memory, new research suggests](https://www.psypost.org/chatgpt-acts-as-a-cognitive-crutch-that-weakens-memory-new-research-suggests/)
55
- [[Cognitive offloading]], [[Sycophancy]]
6+
- [More than a game: some thoughts on David Wiley’s “Random Audits as a Scalable Deterrent to Cheating” – Jon Dron's home page](https://jondron.ca/more-than-a-game-some-thoughts-on-david-wileys-random-audits-as-a-scalable-deterrent-to-cheating/)
7+
- [[Cheating]], [[Artificial intelligence in education]], [[Oral exam]]
8+
- [Mozilla.ai Joins Flower Hub as Launch Partner](https://blog.mozilla.ai/federate-phishing-detection-training-a-url-classifier-without-sharing-browsing-data/)
9+
- [[LLM training]], [[Firefox]], [[Decentralization]]
10+
- [Learn Claude Code Interactively — by Ahmed Nagdy](https://claude.nagdy.me/)
11+
- [[Claude]], [[Code generation]], [[AI engineering]]
12+
- [SuperOptiX AI - Full Stack Agentic AI Framework](https://superoptix.ai/gepa)
13+
- [[AI agents]], [[optimization]], [[autoresearch]], [[AI engineering]], [[hermes]], [[Prompt engineering]], [[Python]]
14+
- [gepa-ai/gepa: Optimize prompts, code, and more with AI-powered Reflective Text Evolution](https://github.com/gepa-ai/gepa)
15+
- [Prompt Optimization with DSPy: GEPA Explained with Python Examples | by Melike Nur Erdoğan | Medium](https://medium.com/@melikedulkadir/prompt-optimization-with-dspy-gepa-explained-with-python-examples-e85f4ea17a8d)
16+
- [Prompt Optimization for Language Models with DSPy GEPA · Hugging Face](https://huggingface.co/learn/cookbook/dspy_gepa)
17+
- https://m.youtube.com/watch?v=vbqvDPB8WTE
18+
- [HKUDS/OpenSpace: "OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/](https://github.com/HKUDS/OpenSpace)
19+
- [[AI Skill]], [[autoresearch]], [[AI agents]], [[AI engineering]]
20+
- [What if the struggle isn't productive? - by Bill McCallum](https://mathematicalmusings.substack.com/p/what-if-the-struggle-isnt-productive?trk=feed_main-feed-card_reshare_feed-article-content)
21+
- [[Productive failure]], [[Direct instruction]], [[Constructivism]]
622
-

journals/2026_03_31.md

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
- [instructkr/claw-code: Better Harness Tools, not merely storing the archive of leaked Claude Code but also make real things done. Now rewriting in Rust.](https://github.com/instructkr/claw-code)
2+
- [[Claude]], [[Rust]], [[Code generation]], [[opencode]], [[AI agents]]
3+
- [Entire Claude Code CLI source code leaks thanks to exposed map file - Ars Technica](https://arstechnica.com/ai/2026/03/entire-claude-code-cli-source-code-leaks-thanks-to-exposed-map-file/)
4+
- [Built-in AI - Chrome Web Store](https://chromewebstore.google.com/detail/built-in-ai/aekdeffgkjegkdbdnkllpaeakcapfjdb?pli=1)
5+
- [[Browser AI]], [[Chrome]], [[Browser extensions]]
6+
- [openai/codex: Lightweight coding agent that runs in your terminal](https://github.com/openai/codex)
7+
- [[AI agents]], [[OpenAI]], [[ChatGPT]], [[Code generation]]
8+
- [The Claude Code Source Leak: fake tools, frustration regexes, undercover mode, and more | Alex Kim's blog](https://alex000kim.com/posts/2026-03-31-claude-code-source-leak/)
9+
- [[Claude]]
10+
-

journals/2026_04_01.md

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
- [OpenClaw: The complete guide to building, training, and living with your personal AI agent](https://www.lennysnewsletter.com/p/openclaw-the-complete-guide-to-building)
2+
- [[openclaw]]
3+
- [open-pencil/open-pencil: AI-native design editor. Open-source Figma alternative.](https://github.com/open-pencil/open-pencil)
4+
- [[Image editor]], [[Open source]], [[Image generation]]
5+
- [I Built This NotebookLM + Gemini Workflow to Destroy AI Fingerprints! | Notion](https://www.notion.so/I-Built-This-NotebookLM-Gemini-Workflow-to-Destroy-AI-Fingerprints-335606421d12802da336fa1b41a04970?source=copy_link)
6+
- [[Prompt engineering]], [[NotebookLM]], [[Writing]], [[AI detection]]
7+
- https://youtu.be/0rzrFCobhy0?si=kSWxtSHBt6Q8u6Qs
8+
- [Sycophantic AI decreases prosocial intentions and promotes dependence | Science](https://www.science.org/doi/10.1126/science.aec8352)
9+
- [[Sycophancy]], [[Prosocial]], [[Cognitive offloading]], [[Artificial intelligence in society]]
10+
- [emdash-cms/emdash](https://github.com/emdash-cms/emdash)
11+
- [[WordPress]], [[Cloudflare]]
12+
- [[2603.27550] Drag or Traction: Understanding How Designers Appropriate Friction in AI Ideation Outputs](https://arxiv.org/abs/2603.27550)
13+
- [[Visual design]], [[Ideation]], [[Artificial intelligence in the workplace]], [[Artificial intelligence in education]], [[Design]], [[Creativity]], [[Friction]], [[Productive failure]], [[Ambiguity]], [[Desirable difficulty]], [[Cognitive offloading]], [[Functional fixedness]], [[Mindset]], [[Web design]]
14+
- >We propose Generative Friction, which introduces intentional disruptions to AI output (fragmentation, delay, ambiguity) designed to transform it from finished product into semi-finished material, inviting human contribution rather than passive acceptance.
15+
- [AI-assisted Grading and Feedback: Why “Approved Tools” Are Not the Whole Compliance Story](https://academicintegrity.org/aws/ICAI/pt/show_detail/616421?layout_name=layout_details&model_name=news_article)
16+
- [[Grading]], [[Artificial intelligence in education]]
17+
- [Developing Syllabus Statements for AI - Center for the Enhancement of Learning and Teaching](https://provost.tufts.edu/celt/online-resources/artificial-intelligence/ai-syllabus-statements/?trk=feed_main-feed-card_feed-article-content)
18+
- [[Course policy]], [[Artificial intelligence in education]]
19+
- [Research and the Development of Educational Assessment: Oxford Review of Education: Vol 26, No 3-4](https://www.tandfonline.com/doi/abs/10.1080/713688540?trk=feed_main-feed-card_feed-article-content)
20+
- [[Assessment]], [[Formative assessment]]
21+
- [SirhanMacx/Claw-ED: Free AI lesson planner that learns your teaching voice. Generate complete lesson packages from your curriculum files. Open source, runs locally, no subscription. pip install clawed](https://github.com/SirhanMacx/Claw-ED?tab=readme-ov-file)
22+
- [[hermes]], [[Lesson plan]], [[Learning Design]], [[AI agents]], [[Artificial intelligence in education]], [[Claude]]
23+
- [Claw-ED — Free AI Lesson Planner for Teachers | Open Source](https://sirhanmacx.github.io/Claw-ED/)
24+
-

journals/2026_04_02.md

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
- [danielmiessler/Personal_AI_Infrastructure: Agentic AI Infrastructure for magnifying HUMAN capabilities.](https://github.com/danielmiessler/Personal_AI_Infrastructure)
2+
- [[AI agents]], [[AI engineering]], [[Claude]]
3+
- https://drphilippahardman.substack.com/p/the-course-is-dying-as-the-unit-of?publication_id=926556&post_id=192819825&isFreemail=true&r=1gwis&triedRedirect=true
4+
- [[Course]], [[Learning Design]], [[Artificial intelligence in the workplace]]
5+
- [Yggdrasil Network | End-to-end encrypted IPv6 networking to connect worlds](https://yggdrasil-network.github.io/)
6+
- [[P2P]], [[Decentralized web]]
7+
- [Yggdrasil is an experimental compact routing scheme that is fully decentralised | Hacker News](https://news.ycombinator.com/item?id=43921624)
8+
- [Mycoria](https://mycoria.org/)
9+
- [meshcore-dev/MeshCore: A new lightweight, hybrid routing mesh protocol for packet radios](https://github.com/meshcore-dev/MeshCore)
10+
- https://github.com/markqvist/Reticulum
11+
- [Yggdrasil Network | Hacker News](https://news.ycombinator.com/item?id=47618100)
12+
- [SQLite Features You Didn’t Know It Had: JSON, text search, CTE, STRICT, generated columns, WAL](https://slicker.me/sqlite/features.htm)
13+
- [[SQLite]]
14+
- [AIventure: Learning about vibe-coding, agents and Gen AI with Gemma 4 - Solutions for Developers  |  Google for Developers](https://developers.google.com/solutions/learn/aiventure)
15+
- [[Vibe coding]], [[Local AI]], [[Open LLM]], [[Gemini]], [[Game development]], [[AI agents]], [[Game-based learning]]
16+
-

journals/2026_04_03.md

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
- [Staged AI Boundaries - Assignment Case Studies](https://ai-assignment-case.vercel.app/)
2+
- [[Assignment]], [[Artificial intelligence in education]]
3+
- [[2602.00070] FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs](https://arxiv.org/abs/2602.00070)
4+
- [[Data sets]], [[Mathematics education]], [[ASSISTments]], [[Intelligent tutoring system]], [[huggingface]], [[Artificial intelligence in education]], [[LLM training]]
5+
- [ASSISTments/FoundationalASSIST · Datasets at Hugging Face](https://huggingface.co/datasets/ASSISTments/FoundationalASSIST)
6+
- [Harness engineering for coding agent users](https://martinfowler.com/articles/harness-engineering.html#HarnessTemplates)
7+
- [[AI engineering]]
8+
- [NousResearch/hermes-agent-self-evolution: ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA](https://github.com/NousResearch/hermes-agent-self-evolution)
9+
- [[hermes]], [[autoresearch]], [[self-improvement]], [[AI engineering]], [[AI agents]]
10+
- [Rigario (@Rigario): "Many are running @NousResearch Hermes Agent now. Here are some practical tips that help a lot, especially if you're coming from OpenClaw: 1. Nightly skill evolution is worth setting up. Link: https://github.com/NousResearch/hermes-agent-self-evolution Pro tip: Add a second cronjob to evaluate the changes so you don't have to. Make sure it stops anything that tries to game the optimization loop. 2. Install Honcho if you're hitting memory issues. It gives proper cross-session recall, memory synthesis, and better long-term storage. Helps avoid repeating the same mistakes or pulling too much context (and wasting tokens). 3. Consider changing the default session timeout and expiry. Especially useful for threads you don't use every day, prevents the agent from losing context unnecessarily. For those migrating from OpenClaw: 4. Expose your OpenClaw agents as OpenAI-compatible endpoints. This lets you run both side-by-side with zero disruption while you transition. Hermes can call them directly, and your existing crons keep working. 5. On day one, start populating your USER.md and MEMORY.md files. Note for OC users: Hermes has a much smaller character limit than OpenClaw, so populate and curate thoughtfully, don't just dump everything in. Quality over quantity helps it learn you faster. 2,200 for memory and 1,375 for user. Hermes works especially well once you integrate it properly into your workflows. Last tip, don't start changing your skin till your agents are actually doing work. You might never stop and go down the rabbit hole... 🤣" | nitter](https://nitter.net/Rigario/status/2039763698584314311#m)
11+
- [[hermes]]
12+
- [plastic-labs/honcho: Memory library for building stateful agents](https://github.com/plastic-labs/honcho?tab=readme-ov-file)
13+
- [[AI memory]], [[hermes]]
14+
- [JUMPERZ (@jumperz): "karpathy is showing one of the simplest AI architectures that actually works.. dump research into a folder, let the model organise it into a wiki, ask questions, then file the answers back in. the real insight is the loop...every query makes the wiki better. it compounds.. now thats a second brain building itself. i think this is so good for agents if applied right instead of pulling from shared memory every session, they build a living knowledge base that stays. your coordinator is not just coordinating tasks anymore.. it is maintaining institutional knowledge so every execution adds something back to the base. the bigger implication is crazy tho. agents that own their own knowledge layer do not need infinite context windows, they need good file organisation and the ability to read their own indexes. way cheaper, way more scalable, and way more inspectable than stuffing everything into one giant prompt." | nitter](https://nitter.net/jumperz/status/2039826228224430323#m)
15+
- [[Knowledge base]], [[Knowledge graph]], [[Wiki]], [[AI memory]], [[autoresearch]], [[AI agents]], [[AI engineering]], [[AI Skill]]
16+
- [The AI Doc’s Falsehoods and False Balance](https://www.aipanic.news/p/the-ai-docs-falsehoods-and-false)
17+
- [[Artificial intelligence Ethics]], [[Bias in algorithms]], [[Artificial intelligence in society]], [[Misinformation]], [[Panic pedagogy]]
18+
- [(2) The Ultimate AI Detection Championship](https://davidwsilva.substack.com/p/the-ultimate-ai-detection-championship)
19+
- [[AI detection]]
20+
- [Hollywood Just Packaged AI Anxiety and Is Bringing It to Theaters: Enter the Apocaloptimists](https://davidwsilva.substack.com/p/hollywood-just-packaged-ai-anxiety)
21+
- [[Artificial intelligence in society]], [[Persuasion]], [[Propaganda]], [[Cognitive biases]], [[Panic pedagogy]], [[Misinformation]]
22+
- [Emotion Concepts and their Function in a Large Language Model](https://transformer-circuits.pub/2026/emotions/index.html)
23+
- [[Emotion]], [[LLM]], [[Neuron]], [[Sycophancy]], [[Human-computer interaction]], [[Machine Learning]], [[Artificial intelligence]], [[Explainable AI]]
24+
- [Explainable artificial intelligence - Wikipedia](https://en.wikipedia.org/wiki/Explainable_artificial_intelligence)
25+
- [[Explainable AI]], [[Reasoning]], [[Neural network]], [[Machine Learning]], [[Neurosymbolic AI]], [[Artificial intelligence]], [[LLM]], [[Explanation]], [[Explorable explanations]]
26+
- [GPT-5.3 and GPT-5.4 in ChatGPT | OpenAI Help Center](https://help.openai.com/en/articles/11909943-gpt-53-and-gpt-54-in-chatgpt)
27+
- [[ChatGPT]], [[Reasoning]], [[copilot]], [[codex]]
28+
-

pages/Explainable AI.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
- [[Machine Learning]]
2+
- [[Artificial intelligence]]
3+
- [[Neural network]]
4+
- [[Explanation]]
5+
- [[Neurosymbolic AI]]
6+
-

pages/Explanation.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,5 +4,7 @@
44
- What is an explanation of [[Cognitive psychology]] https://journals.sagepub.com/doi/10.1111/j.1467-9280.1992.tb00017.x
55
- [[Refutation text]],[[Impasse]] https://www.researchgate.net/publication/225137508_Are_instructional_explanations_more_effective_in_the_context_of_an_impasse
66
- Why they often don't work https://www.researchgate.net/publication/254303556_Why_Instructional_Explanations_Often_Do_Not_Work_A_Framework_for_Understanding_the_Effectiveness_of_Instructional_Explanations
7-
8-
[[Communication]]
7+
- [[Communication]]
8+
- [[Explorable explanations]]
9+
- [[Explainable AI]]
10+
-

0 commit comments

Comments
 (0)