ivorscott
@ivorscott.com
Art, Engineering, and Go.
💻 linkedin.com/in/ivorscott
🎨 ivorscott.com
💻 linkedin.com/in/ivorscott
🎨 ivorscott.com
Reposted by ivorscott
Reposted by ivorscott
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.
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.
www.forkingpaths.co
June 19, 2025 at 10:44 AM
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.
Useful listing of mcp servers. mcp.so
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.
mcp.so
June 19, 2025 at 12:05 PM
Useful listing of mcp servers. mcp.so
Reposted by ivorscott
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
"A Conjecture on a Fundamental Trade-Off between Certainty and Scope in Symbolic and Generative AI"
Version 2
papers.ssrn.com/sol3...
3/3
June 11, 2025 at 7:30 PM
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
"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.
🔥 Hot Repo！ 🔥 (100+ new stars)
📦 yamadashy / repomix
⭐ 10,219 (+114)
🗒 TypeScript
📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or ot...
📦 yamadashy / repomix
⭐ 10,219 (+114)
🗒 TypeScript
📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or ot...
GitHub - yamadashy/repomix: 📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) o...
github.com
June 19, 2025 at 8:58 AM
This project looks promising.
Doing less work reduces brain engagement? 😮 shocking…
"ChatGPT users had the lowest brain engagement and “consistently underperformed at neural, linguistic, and behavioural levels.” Over the course of several months, ChatGPT users got lazier with each subsequent essay, often resorting to copy-and-paste."
time.com/7295195/ai-c...
time.com/7295195/ai-c...
ChatGPT's Impact On Our Brains According to an MIT Study
The study, from MIT Lab scholars, measured the brain activity of subjects writing SAT essays with and without ChatGPT.
time.com
June 19, 2025 at 8:20 AM
Doing less work reduces brain engagement? 😮 shocking…
TL;DR: Does it really make you faster if you need to maintain code you don't understand? You can’t have both speed and clarity without effort. blog.miguelgrinberg.com/post/why-gen...
Why Generative AI Coding Tools and Agents Do Not Work For Me
People keep asking me If I use Generative AI tools for coding and what I think of them, so this is my effort to put my thoughts in writing, so that I can send people here instead of having to repeat…
blog.miguelgrinberg.com
June 17, 2025 at 3:37 AM
TL;DR: Does it really make you faster if you need to maintain code you don't understand? You can’t have both speed and clarity without effort. blog.miguelgrinberg.com/post/why-gen...
My takeaways from the Building Agents with MCP in Go workshop.
June 17, 2025 at 2:04 AM
My takeaways from the Building Agents with MCP in Go workshop.
Reposted by ivorscott
June 16, 2025 at 8:11 AM
6 Agentic Coding Tips
1. Guide don't dictate
2. Review everything
3. Test incrementally
4. Patten consistently
5. Simple is better
6. Every AI output should be filtered through human
1. Guide don't dictate
2. Review everything
3. Test incrementally
4. Patten consistently
5. Simple is better
6. Every AI output should be filtered through human
June 16, 2025 at 10:37 AM
6 Agentic Coding Tips
1. Guide don't dictate
2. Review everything
3. Test incrementally
4. Patten consistently
5. Simple is better
6. Every AI output should be filtered through human
1. Guide don't dictate
2. Review everything
3. Test incrementally
4. Patten consistently
5. Simple is better
6. Every AI output should be filtered through human
Reposted by ivorscott
@kentbeck.com is a legend in software engineering: and after coding for 52 years, he's never had more fun than now, he told me. Why? AI agents brought back the joy of creating software without the stuff that he's started to hate about coding.
Watch/listen:
• YouTube: youtu.be/aSXaxOdVtAQ (cont'd)
Watch/listen:
• YouTube: youtu.be/aSXaxOdVtAQ (cont'd)
June 11, 2025 at 4:29 PM
@kentbeck.com is a legend in software engineering: and after coding for 52 years, he's never had more fun than now, he told me. Why? AI agents brought back the joy of creating software without the stuff that he's started to hate about coding.
Watch/listen:
• YouTube: youtu.be/aSXaxOdVtAQ (cont'd)
Watch/listen:
• YouTube: youtu.be/aSXaxOdVtAQ (cont'd)
Reposted by ivorscott
So you would like to write more reliable software ?
I just published a presentation about how to model software with TLA+, meant for software engineers, not mathematicians/logicians.
speakerdeck.com/fgm/a-tla-pl... #tlaplus
I just published a presentation about how to model software with TLA+, meant for software engineers, not mathematicians/logicians.
speakerdeck.com/fgm/a-tla-pl... #tlaplus
A TLA+ intro for Software engineers
This presentation introduces TLA+, a formal specification language for concurrent systems.
Unlike most existing reference sources, it is meant for u…
speakerdeck.com
March 19, 2025 at 12:41 PM
So you would like to write more reliable software ?
I just published a presentation about how to model software with TLA+, meant for software engineers, not mathematicians/logicians.
speakerdeck.com/fgm/a-tla-pl... #tlaplus
I just published a presentation about how to model software with TLA+, meant for software engineers, not mathematicians/logicians.
speakerdeck.com/fgm/a-tla-pl... #tlaplus
So I've been avoiding a deep dive into MCP–only recently receiving a brief introduction from watching @bretfisher.com live shows. Is it fate that the Go workshop I purchased for next week was replaced last minute? Guess what the topic is.
a man wearing sunglasses and a suit is saying it is inevitable
ALT: a man wearing sunglasses and a suit is saying it is inevitable
media.tenor.com
June 10, 2025 at 9:55 AM
So I've been avoiding a deep dive into MCP–only recently receiving a brief introduction from watching @bretfisher.com live shows. Is it fate that the Go workshop I purchased for next week was replaced last minute? Guess what the topic is.
I wasn’t aware of the subtle differences between AI and ML Engineering. Interesting read.
The AI Engineering Stack
Three layers of the AI stack, how AI engineering is different from ML engineering and fullstack engineering, and more. An excerpt from the book AI Engineering by Chip Huyen
open.substack.com
June 5, 2025 at 2:14 AM
I wasn’t aware of the subtle differences between AI and ML Engineering. Interesting read.
Opinions spark healthy discussion. We can’t afford to remain passive. The cultural divide over AI, whether it’s friend or foe, misses the point —it’s both. This duality demands more investigation. Yet, the sheer speed of information today is dismantling our capacity for reflection.
I am disappointed in the AI discourse steveklabnik.com/writing/i-am...
I am disappointed in the AI discourse
steveklabnik.com
May 29, 2025 at 8:43 AM
Opinions spark healthy discussion. We can’t afford to remain passive. The cultural divide over AI, whether it’s friend or foe, misses the point —it’s both. This duality demands more investigation. Yet, the sheer speed of information today is dismantling our capacity for reflection.
Reposted by ivorscott
I wonder why Go programmers don’t engage in large public discussions on how obtuse other languages are.
Maybe they’re too busy shipping real world code to production 🤔
Maybe they’re too busy shipping real world code to production 🤔
May 25, 2025 at 12:18 PM
I wonder why Go programmers don’t engage in large public discussions on how obtuse other languages are.
Maybe they’re too busy shipping real world code to production 🤔
Maybe they’re too busy shipping real world code to production 🤔
Reposted by ivorscott
Finally did it. I wrote down how to build a code-editing agent.
In 315 lines of code. And yes, it works. Very well.
There is no moat.
Read it here: ampcode.com/how-to-build...
In 315 lines of code. And yes, it works. Very well.
There is no moat.
Read it here: ampcode.com/how-to-build...
April 15, 2025 at 7:56 PM
Finally did it. I wrote down how to build a code-editing agent.
In 315 lines of code. And yes, it works. Very well.
There is no moat.
Read it here: ampcode.com/how-to-build...
In 315 lines of code. And yes, it works. Very well.
There is no moat.
Read it here: ampcode.com/how-to-build...
If only research were easier to trace this wouldn’t take months to uncover.
How to make a splash in AI economics: fake your data
YouTube video by Pivot to AI
youtu.be
May 23, 2025 at 6:27 AM
If only research were easier to trace this wouldn’t take months to uncover.
Reposted by ivorscott
#Docker now has three major AI features. A built-in chatbot, a LLM host, and a MCP tool server and library. I explain what they are, and how to use them
www.bretfisher.com/docker-ai-mo...
www.bretfisher.com/docker-ai-mo...
Docker AI, Model Runner, and MCP Toolkit
Docker now has three major AI features. I'll explain what they are and how to use them together.
www.bretfisher.com
May 18, 2025 at 8:19 PM
#Docker now has three major AI features. A built-in chatbot, a LLM host, and a MCP tool server and library. I explain what they are, and how to use them
www.bretfisher.com/docker-ai-mo...
www.bretfisher.com/docker-ai-mo...
Reposted by ivorscott
Found this tonight and it's a really solid read on the Go runtime. Definitely a long post but it's got a lot of useful info in it.
Learned a lot about things that I haven't really dug into before from it.
nghiant3223.github.io/2025/04/15/g...
Learned a lot about things that I haven't really dug into before from it.
nghiant3223.github.io/2025/04/15/g...
Go Scheduler
↑ ↓
nghiant3223.github.io
May 18, 2025 at 5:59 AM
Found this tonight and it's a really solid read on the Go runtime. Definitely a long post but it's got a lot of useful info in it.
Learned a lot about things that I haven't really dug into before from it.
nghiant3223.github.io/2025/04/15/g...
Learned a lot about things that I haven't really dug into before from it.
nghiant3223.github.io/2025/04/15/g...