ivorscott

ivorscott

@ivorscott.com

✨ ivorscott.com

31 followers70 following47 posts

ivorscott reposted

Russ Cox
@swtch.com

“There’s a tidal wave coming. You can see it. We can all see it. Are you going to lay down and die, or are you going to do something about it?” Be ready to patch your systems, repeatedly, for at least the next 12 months.

This post is unavailable.

ivorscott reposted

Jason Lengstorf
@jason.energy

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...

jason.energyPlease stop multitasking. I’m begging you. Please.The greatest trick we ever pulled on ourselves as knowledge workers was convincing ourselves we could juggle multiple projects with no consequences.
Gergely Orosz@gergely.pragmaticengineer.com

The more I use AI tools, the more I have to admit that I'm not that much more productive... I simply FEEL that much more productive. In reality, the context switching of kicking several things off wipes out my perceived productivity gains. At least in many/most cases!

ivorscott
@ivorscott.com

🫠

Gergely Orosz@gergely.pragmaticengineer.com

This is either brilliant or scary: Anthropic accidentally leaked the TS source code of Claude Code (which is closed source). Repos sharing the source are taken down with DMCA. BUT this repo rewrote the code using Python, and so it violates no copyright & cannot be taken down!

ivorscott reposted

Gergely Orosz
@gergely.pragmaticengineer.com

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!

ivorscott
@ivorscott.com

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?

ivorscott reposted

Julia Angwin
@juliaangwin.com

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...

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

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.

ivorscott reposted

Kent Beck
@kentbeck.com

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.

ivorscott
@ivorscott.com

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

Gergely Orosz@gergely.pragmaticengineer.com

On one end, the Anthropic team is a massive user of AI to write code (80%+ of all code deployed is written by Claude Code). They ship amazingly fast. On the other hand, seeing these beyond terrible reliability numbers suggests there might be a downside to all this speed:

View full thread
ivorscott
@ivorscott.com

5. Langchaingo is a great library for orchestrating an Agent's business logic, which may involve getting context from an MCP server, or chaining LLMs if desired. Langchaingo doesn't work with MCP by default––so you'll need an adapter. github.com/dmahlow/lang...

github.comGitHub - dmahlow/langchaingo-mcp-adapter: A Go adapter that bridges LangChain Go tools with Model Context Protocol (MCP) servers.A Go adapter that bridges LangChain Go tools with Model Context Protocol (MCP) servers. - dmahlow/langchaingo-mcp-adapter

ivorscott reposted

Brian Klaas
@brianklaas.bsky.social

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.

forkingpaths.coThe Death of the Student Essay—and the Future of CognitionOne 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.
ivorscott
@ivorscott.com

This project looks promising.

GitHub Trending@github-trending.bsky.social

🔥 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...

github.comGitHub - 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...
ivorscott
@ivorscott.com

Doing less work reduces brain engagement? 😮 shocking…

Julien Hoez@julienhoez.eu

"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.comChatGPT's Impact On Our Brains According to an MIT StudyThe study, from MIT Lab scholars, measured the brain activity of subjects writing SAT essays with and without ChatGPT.
ivorscott
@ivorscott.com

Miguel has a point but I'm optimistic. Painting didn't die when the camera was invented––it evolved. Photorealism emerged, abstraction flourished and new styles were born in response. This tech is in it's trail phase, in the future, we will develop new techniques inspired by these challenges.

View full thread
ivorscott
@ivorscott.com

1. Claude Sonnet 4 is expensive for a reason––it's coding quality exceeds Open AI GPT 4.1. Even when prompted to stay minimal the responses were noticeably more elaborate. I only spent $2.50 using GPT 4.1 for the 7 hour workshop while the person next to me racked up $9 using Sonnet 4.

ivorscott
@ivorscott.com

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

ivorscott reposted

Frédéric G. MARAND
@fgmarand.bsky.social

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

speakerdeck.comA TLA+ intro for Software engineersThis presentation introduces TLA+, a formal specification language for concurrent systems. Unlike most existing reference sources, it is meant for u…
ivorscott
@ivorscott.com

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.

ivorscott
@ivorscott.com

I recommend reading “Speed and Politics” by cultural theorist Paul Virilio. He explores how velocity shapes power, culture, and perception. Insights that feel more urgent now than ever in the AI era.