Note-taking Meditations - Part 1 | Ivor Scott The first in a series of personal writings on note-taking. AI-assisted note-taking: summarizing books, file structure, analogies and diagrams.

ivorscott.com/articles/not...

it seems more important than ever to give real thought to the difference between “busy” and “productive”. it doesn’t matter how fast the buttons get pushed if nothing of value comes out of that flurry of activity

I’ve written about this a lot over the years
jason.energy/context-swit...

I Went All-In on AI. The MIT Study Is Right. My all-in AI experiment cost me my confidence

“Own your craft. Use the tools. Don’t let the tools use you.”

Sycophantic AI decreases prosocial intentions and promotes dependence Despite rising concerns about sycophancy—excessive agreement or flattery from artificial intelligence (AI) systems—little is known about its prevalence or consequences. We show that sycophancy is wide...

"...even a single interaction with sycophantic AI reduced participants’ willingness to take responsibility and repair interpersonal conflicts, while increasing their own conviction that they were right."

Draw the Route | Ivor Scott AI can generate a curriculum in seconds. Deciding which parts matter, in what order, and when a learner is drifting, that job still belongs to the educator.

What do educators offer that AI can't?

ivorscott.com/articles/dra...

🫠

Ironic how Anthropic sells Claude Code security reviews positioned as something v powerful (costing $15-25 per PR review), and being clear they use it on all PRs... then leaking all of Claude Code's code thanks to publishing their sourcemap.

AI won't save you from yourself!

1. Collect ideas. What is there to know?
2. Prioritise. What should you know?
3. Sort. In what order?
4. Associate. Associate your progress with happiness. (Feel terrible if you’re off track and celebrate if you’re on track —consequence and reward).
5. Teach. How can you explain it?

Grammarly Is Facing a Class Action Lawsuit Over Its AI ‘Expert Review’ Feature The feature, which Grammarly shut down Wednesday, presented editing suggestions as if they came from established authors and academics—without their consent.

I'm suing Grammarly over its paid AI feature that presented editing suggestions as if they came from me - and many other writers and journalists - without consent.

State law requires consent before someone's name can be used for commercial purposes.

www.wired.com/story/gramma...

GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automatically AI agents running research on single-GPU nanochat training automatically - karpathy/autoresearch

github.com/karpathy/aut...

Attempt ambitious goals without doubting yourself.

Even if you make it halfway, that’s success.

Even if you fail at the beginning, that’s convenient.

Learn from your mistakes and choose the right goals for the present and future you.

AI Cognitive Debt: The Crisis Nobody Sees Coming YouTube video by Imran Gardezi

Agent skills modeling explicit coding conventions improve clarity and limit surprises.

The companies that deprioritise the soft skills will suffer. As always.

I hate the re-soloing of development. We were so close to learning social skills, creating community, encouraging creativity & purpose, & applying empathy. Easier to manage if each of us is so busy with our genieswarms that we don't have time to talk & reflect.

How to Trick Your Brain into Doing Difficult Things A Neuroscientist’s 7 Proven Ways to Get Yourself to Do What Matters

open.substack.com/pub/brainhea...

Not surprisingly tbh. They keep changing things. There’s a new feature every few days. That’s why there’s 5k+ issues on GitHub. 👌

From Writing Lines to Writing Intent | Ivor Scott Coding hasn't disappeared. It has moved upstream from syntax to specification. In an agentic workflow, the developer's value lies in defining intent precisely, not in typing code faster.

ivorscott.com/articles/fro...

Let’s adopt shenanigans.

No. Looks clean, thanks for sharing. I find it interesting how some people embrace the word “vibe coding” while others consider it a curse word—the latter often distinguishing themselves from vibe coding by redefining it as shipping generated code to production.

I’m also considering notion’s MCP server for ingesting technical proposal documents. Each document defines a software project—its name, problem, scope, dependencies, components, endpoints etc. My intention is to connect VScode to this context for an agentic coding workflow.

@bretfisher.com some additional notes about my workshop experience.

In a workshop last week, I built a cli for desktop automation—it controlled the mouse & keyboard. Next, I made an MCP sever based on its functionality, exposing the important functions as MCP cmds. Then, I connected to the MCP sever and an LLM in a middleman script to automate a specific task.

New blog post: "Why computational reproducibility matters"

blog.khinsen.net/posts/2025/0...

🧪

The Death of the Student Essay—and the Future of Cognition One professor's reflections on the end of an era, as AI tools such as ChatGPT have murdered the student essay (RIP). Here's why that threatens the future of human cognition—and how to save ourselves.

After the latest round of grading papers, I wrote about AI, ChatGPT, the death of the student essay, and what it means for the future of human cognition.

MCP Servers The largest collection of MCP Servers, including Awesome MCP Servers and Claude MCP integration. Search and discover MCP servers to enhance your AI capabilities.

Useful listing of mcp servers. mcp.so

The paper provides a formal framework for what AI practitioners have long suspected.

"A Conjecture on a Fundamental Trade-Off between Certainty and Scope in Symbolic and Generative AI"
Version 2
papers.ssrn.com/sol3...
3/3

This project looks promising.

On a serious note, is all brain engagement productive?

Doing less work reduces brain engagement? 😮 shocking…

#gopherconeu