Announced the RustQuest community project at the @rust.nyc meetup yesterday! I hope this can grow as a resource to effectively teach young students #rustlang + CS concepts in tandem! special thanks to @colelawrence.com and @busysp.bsky.social for support! github.com/nrposner/rus...

using LLMs to refactor and my new favorite prompt is becoming: "Ask me clarifying questions about any uncertainty you have about the refactoring." This is saving me so many little headaches where the LLM changed the approach in subtle ways.

Absolutely killer combination for system architecture design: - Gemini 2.5 Pro for preparing interview questions - ChatGPT Voice mode for interview - Gemini 2.5 Pro for writing a technical write-up + updated overview instructions file for ChatGPT

This is our first month to have two events in a long time! Check it out if you're in NYC

Any tips on hiring AI product engs for a startup? Practical experience designing and troubleshooting tool-loops. $300k-$450k remote if they connect product thinking and AI pipeline setup, design, and devops experience. This is a hypothetical role at the moment, just looking for advice.

I started working on an open-source todo "UI" that syncs with a markdown file, since all my TODOs are in markdown for AI editing context. Also has a - Pomodoro timer - Customizable sound cues for break start, end, task completion, etc github.com/colelawrence...

Made a fun little helper for React to make it possible to "click" buttons without clicking when you have a input focused. Was having some trouble with debugging some focusout issue gist.github.com/colelawrence...

Sometimes I fall back into the habit of writing code with a keyboard, and I have to fight that habit formed from the last 10+ years For LLM coding to pay off, you gotta learn how to keep the context/session "on the rails", and getting "on the rails" is the hardest hurdle to get over

with AI, I seem to spend more of my time than ever designing the codebase's framework in a composable + testable way, because the payoff is huge when you know how each individual file is more complicated, but the total codebase is at a fixed complexity even with added features

I'm excited to be launching this new website for the next phase of @forethink.ai 🎉 I hope this page better communicates how we can amplify teams working in the browser by enriching the webpages they visit with private information from their company and peers–all with extreme care for data privacy!

Great little write-up of today's best toolset for local LLMs Thanks for writing, Abishek ❤️

I’m noticing a trend in “AI fatigue” that comes 10x with independent agents (like Devin) compared to human in the loop agents (like Windsurf/Cursor) Oddly enough, I first started noticing it with o1 pro, because the answers take a long time and are so rich with information, that I lose track

Really enjoyed this write up on the new Devin AI tool. It looks like today, it might be annoying to use, but LLMs for coding were annoying to use at the start, too.

🦀 Do you have a Rust project to share? Are you doing anything in four hours? Join the #RustEastCoast "Show and tell" at 2pm ET today in our Discord! #RustLang #BuildInPublic Get feedback on your work and share your successes!

Bernard is working on a durable executions workflow engine similar to Temporal / Inngest, but for #Rustlang This is a really nice demonstration of how the idea of code “time traveling” complements durable execution!

Thoroughly enjoyed this write up of the recent ultralytics compromise

By popular request, here's how to add Bluesky replies as your blog's comment section! This requires some technical know-how for now, but I'm hoping that we see some no-code solutions for this pop up soon, like Ghost or Wordpress plugins. emilyliu.me/blog/comments

Throwback to Feb 2020 👀, when I first started designing StoryAI–a textual low-code editor. After struggling to explain how the editing should "feel", I ended up having to dust off my After Effects skills one weekend to draw this up! #buildinpublic #design #nocode #toolsforthought #rip #storyai

Two things I didn't realize @windsurfai.bsky.social was going to do so well: 1. Quickly fall into a rhythm of writing impl, writing tests, testing, and iterating (using `vitest run [filename]` 2. Analyzing `.d.ts` files to try to understand how to use my deps bravo 👏 #ai #llms #dev #typescript

Immediately pinned these new 🦋 lists from @simonwillison.net bsky.app/profile/simo... - LLM Labs (folks from OpenAI, Anthropic, etc) bsky.app/profile/simo... - AI Journalists #ai #llms #bluesky

🦀 Calling all #rustacean and passionate #rustlang friends to join our virtual community at rusteastcoast.com! We have a recently started reading club started by a member, a monthly show-and-tell, and occasional talks! And there are active location channels for NYC, Boston, and others!

Another cool starter pack for local-first people to follow! 🦋

Just found @mxb.dev's whimsical.club - a curation of websites with small joyful interactions. I love all these little handcrafted interactions #webdev #webdesign

🧵 Trying out @windsurfai.bsky.social for a few days - here are my initial thoughts on this new AI-powered editor (1/6) #windsurf #vscode #ai #cursor #programming

Great collection of accounts for all of you who are getting started! 🦋

Thinking about how to create personalized vignettes like this with my browser extension for teams

I'm looking for other programmers sharing their prompt workflows and experiences trying new AI tools on here! I need a few more to create a starter pack. #llms #cursor #ai #vscode @swyx.io + @wesbos.com + @simonwillison.net + @stevekrouse.com to start

📝 New guideline prompt `feature-doc-guideline.md` helps you create `docs/new-feature-feature.md` files. Every new feature starts with this guideline which provides a stable understanding for all other parts of the implementation phases. #ai #cursor #vscode #llms gist.github.com/colelawrence...