MMM
907 posts

MMM retweetledi
MMM retweetledi

40% of the code Claude writes for you is wasted. you're paying for the rewrite.
a 65-line markdown file fixes it. 120,000 developers have starred it.
the author tested it on "30 codebases over 6 weeks" and reported a mistake rate drop from 41% to either 11% or 3%
depending on whether you read the headline or the body.
the irony is that the article is right.
CLAUDE.md is the most under-leveraged file in your stack.
65 lines of behavioral rules outperform a 4,000-token preferences dump.
"be careful" is useless. testable imperatives are gold.
"be senior" doesn't work Claude already thinks it is.
the 4 rules that ship the most leverage:
/ state assumptions, never guess silently
/ minimum code, nothing speculative
/ surgical changes, don't refactor adjacent code
/ define success, loop until verified
compliance: ~80%. mistake rate: from ~40% to single digits.
no human caught the contradicting numbers in the title.
nobody had to.
Mnimiy@Mnilax
English
MMM retweetledi

> be Andrej Karpathy
> builds neural nets before anyone calls them AI
> joins OpenAI. helps train GPT.
> becomes head of AI at Tesla
> teaches the world how LLMs actually work. for free.
> leaves Tesla. starts making YouTube videos
> 1M subscribers. still free.
> posts a casual observation about LLM coding habits
> names 4 problems nobody was talking about
> one developer turns it into a single CLAUDE.md file
> 84,000 stars in days
> zero dependencies. zero cost.
> Karpathy didn't even write the repo
> just told the truth
> the person who understands the problem
> doesn't always need to build the solution
> sometimes one tweet is enough
Kirill@kirillk_web3
A SINGLE CLAUDE.md FILE JUST HIT #1 ON GITHUB TRENDING. 82,100 stars. 7.8k forks. zero dependencies. Bookmark this before you forget. And your Claude will start working differently. 4 principles. one file. Karpathy's LLM coding habits. distilled. > think before coding. > simplicity first. > surgical edits only. > goal-driven targets before starting. swap it into your CLAUDE.md today. your Claude Code becomes a different tool. Read it today. Link below. Claude → Skills → CLAUDE.md → Better Code → Better Systems → Money
English
MMM retweetledi

Anthropic's applied AI team just dropped a 24-minute workshop on how to actually prompt Claude properly.
Free. From the people who built it.
You've been prompting Claude for months without the 6 elements they teach in this.
I built a skill that applies them automatically. Full guide below.
Bookmark it.
Follow @codewithimanshu for more high-signal content that actually moves your skills forward.
English
MMM retweetledi
MMM retweetledi

Opus 4.7 feels more intelligent, agentic, and precise than 4.6. It took a few days for me to learn how to work with it effectively, to fully take advantage of its new capabilities.
Will post a few more tips throughout the day, starting with this blog post: claude.com/blog/best-prac…
English
MMM retweetledi

Me at 3 am realizing I've been suffering for years… and it took just 1 fvckin free article.
Defileo🔮@defileo
English
MMM retweetledi

MMM retweetledi

We are completely humbled by the amazing response to our launch last week! 🫶 Now, we want to help you get the absolute best results from Stitch.
In this new video, David East walks you through how to consistently get premium results.
We also launched a new prompt enhancer (located under ‘+’ menu) to help you quickly collaborate on your vision before you submit your first prompt.
Stitch doesn't replace the design process—it is a tool for fast exploration and refinement, which is most effective when you step into the role of Creative Director.
Here are David's top strategies for taking your designs from generic to amazing:
🧠 Start with Intent: Define exactly who the design is for and how you want them to feel before you start building.
🎨 Enhance your prompt: You can use the new prompt enhancer (under the ‘+’ button’) to teach you design language and swap abstract words like "sporty" for tangible aesthetic descriptions like "high-end stationery" or "architectural limestone".
📐 Master Color Hierarchy: Treat colors as visual weight—Neutral for the canvas, Primary for ink, and Tertiary for your loudest accents.
Watch the full breakdown and see the transformation here👇images in 🧵
English
MMM retweetledi
MMM retweetledi

Just added a Pretext skill to GStack tonight (Pretext came out a couple days ago, created by the brilliant @_chenglou)
In Claude Code type:
> Install GStack
> /design-html
I think this might be the 2 line fastest way to try Pretext to make hyper-responsive HTML designs
English
MMM retweetledi

MMM retweetledi
MMM retweetledi

My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
English
MMM retweetledi
MMM retweetledi

google just mass-murdered every phone-based job with one API.
real-time voice agent. sub-second latency. filters background noise. follows complex instructions. 90+ languages.
receptionists, appointment schedulers, tier 1 support, all replaceable with a few lines of python.
want to make money off this?
→ pick a niche that lives on calls (dental clinics, salons, restaurants, real estate)
→ build a voice agent that answers, books appointments, handles FAQs
→ connect to their booking system via function calling
→ charge $500/mo. they're paying a human $3k/mo for one line. your agent handles unlimited calls simultaneously.
the window is now. in 6 months everyone will be doing this.
Google AI Studio@GoogleAIStudio
English



