Olivia
Online
The Coding Mermaid π§ββοΈ
@coding_mermaid
Frontend Engineer π©π½βπ»
Graduated in marine biology π¬
Mentor & Teacher β¨
@girlcoderec ambassador π opinions my own
wonderland
Joined March 2011
184 Following
194 Followers
864 Posts
Β Pinned Tweet
This last Saturday was my first time as an in-person speaker, presenting the talk:
"Nevertheless don't quit coding π¦- my advice to youπ"
focused on career switch and self-care.
Thank you so much for the opportunity @GeekGirlsPT π
#careerswitch #womenintech
New in Claude Code: /ultraplan
Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal.
Available now in preview for all users with CC on the web enabled.
What if your GitHub contribution graph wasn't just green squares, but an actual living garden?
Meet GitGarden π³ πΈ π¦ πΏ
https://t.co/XTxHLxgGI5
Who to follow
Jakub Andrzejewski
@jacobandrewsky
Fullstack Developer β’ @GoogleDevExpert in Web Perf β’ @nuxt_js Ecosystem Team
Daniel Kelly
@danielkelly_io
Father, Husband, Human Being, Teacher/Content Creator @VueSchool_io, Web Dev, tweets about @vuejs, @nuxt_js, @laravelphp, and dev life
CalyxOS
@CalyxOS
Privacy focused mobile phone operating system built on top of the android open source project. Produced as part of the mission of the non-profit @calyxinstitute
This is crazy. The week just started
Computer use is now in Claude Code.
Claude can open your apps, click through your UI, and test what it built, right from the CLI.
Now in research preview on Pro and Max plans.
i deleted half my Claude setup last week and every output got BETTER
sounds backwards, but anthropic's own team just explained exactly why it works.
here's the one prompt that tells you what to cut (and you don't even have to paste anything):
this is what happens to everyone...
you get a bad output, so you add a rule to your skills. "be more concise."
next week, another bad output. another rule. "use a casual tone."
but a month later, something else breaks. "always explain technical terms."
you keep stacking, and it feels productive because you're fixing problems as they come up.
but 3 months in, you've got 30 rules piled on top of each other.
some of them contradict each other ("be concise" and "always explain your reasoning" are fighting).
some of them fix problems that the model doesn't even have anymore.
and the model is trying to follow all of them at once, which means it's doing none of them well.
it's like handing a chef a 47-step recipe when they only need 12.
the extra 35 steps slow the chef down, make them second-guess the parts they already know, and the dish comes out worse than if you'd just let them cook.
that's what over-prompting does.
anthropic just published a piece on how they build claude code (the ai coding agent).
their own engineering team found that their scaffolding was making the ai worse
which means your custom instructions are almost certainly doing the same thing.
so here's the actionable move...
instead of manually reading through your setup line by line, just tell claude to audit itself.
if you're in claude's desktop app, claude already has access to your:
claude[.]md (the file where your preferences and rules live), your skills folder (where your reusable instruction files are stored), your context files, everything.
just open claude code/cowork and say this:
β
"read my entire setup before responding. check my claude .md, every skill in my skills folder, every file in my context folder, and any other instruction files you can find.
then go through every rule, instruction, and preference you found. for each one, tell me:
1. is this something you already do by default without being told?
2. does this contradict or conflict with another rule somewhere else in my setup?
3. does this repeat something that's already covered by a different rule or file?
4. does this read like it was added to fix one specific bad output rather than improve outputs overall?
5. is this so vague that you'd interpret it differently every time? (ex: 'be more natural' or 'use a good tone')
then give me a list of everything you'd cut with a one-line reason for each, a list of any conflicts you found between files, and a cleaned up version of my claude.md with the dead weight removed."
β
one message. claude goes and reads your entire setup, audits it, and comes back with exactly what to cut and why.
you don't dig through files, you don't read every rule yourself. it does the whole thing.
once you get the results, don't just blindly delete everything it flags.
here's the process:
1. read what it flagged and why
2. delete the flagged rules
3. run your 3 most common tasks with the trimmed setup
4. did the output stay the same or get better? the deleted rules were dead weight
5. did something specific break? add back just that one rule
the goal is to find the minimum viable setup that gets you the output you want.
your ai setup should be getting simpler over time.
addition by subtraction baby
![itsolelehmann's tweet photo. i deleted half my Claude setup last week and every output got BETTER
sounds backwards, but anthropic's own team just explained exactly why it works.
here's the one prompt that tells you what to cut (and you don't even have to paste anything):
this is what happens to everyone...
you get a bad output, so you add a rule to your skills. "be more concise."
next week, another bad output. another rule. "use a casual tone."
but a month later, something else breaks. "always explain technical terms."
you keep stacking, and it feels productive because you're fixing problems as they come up.
but 3 months in, you've got 30 rules piled on top of each other.
some of them contradict each other ("be concise" and "always explain your reasoning" are fighting).
some of them fix problems that the model doesn't even have anymore.
and the model is trying to follow all of them at once, which means it's doing none of them well.
it's like handing a chef a 47-step recipe when they only need 12.
the extra 35 steps slow the chef down, make them second-guess the parts they already know, and the dish comes out worse than if you'd just let them cook.
that's what over-prompting does.
anthropic just published a piece on how they build claude code (the ai coding agent).
their own engineering team found that their scaffolding was making the ai worse
which means your custom instructions are almost certainly doing the same thing.
so here's the actionable move...
instead of manually reading through your setup line by line, just tell claude to audit itself.
if you're in claude's desktop app, claude already has access to your:
claude[.]md (the file where your preferences and rules live), your skills folder (where your reusable instruction files are stored), your context files, everything.
just open claude code/cowork and say this:
β
"read my entire setup before responding. check my claude .md, every skill in my skills folder, every file in my context folder, and any other instruction files you can find.
then go through every rule, instruction, and preference you found. for each one, tell me:
1. is this something you already do by default without being told?
2. does this contradict or conflict with another rule somewhere else in my setup?
3. does this repeat something that's already covered by a different rule or file?
4. does this read like it was added to fix one specific bad output rather than improve outputs overall?
5. is this so vague that you'd interpret it differently every time? (ex: 'be more natural' or 'use a good tone')
then give me a list of everything you'd cut with a one-line reason for each, a list of any conflicts you found between files, and a cleaned up version of my claude.md with the dead weight removed."
β
one message. claude goes and reads your entire setup, audits it, and comes back with exactly what to cut and why.
you don't dig through files, you don't read every rule yourself. it does the whole thing.
once you get the results, don't just blindly delete everything it flags.
here's the process:
1. read what it flagged and why
2. delete the flagged rules
3. run your 3 most common tasks with the trimmed setup
4. did the output stay the same or get better? the deleted rules were dead weight
5. did something specific break? add back just that one rule
the goal is to find the minimum viable setup that gets you the output you want.
your ai setup should be getting simpler over time.
addition by subtraction baby](https://pbs.twimg.com/media/HEGNR64boAA8x4U.jpg)
You can now enable Claude to use your computer to complete tasks.
It opens your apps, navigates your browser, fills in spreadsheetsβanything you'd do sitting at your desk.
Research preview in Claude Cowork and Claude Code, macOS only.
Hi @Lovable, I'm really impressed with the new features you released today!
Could we please have a nice preview for videos, PDFs, and presentations? π Thank youu
@claudeai Maybe you feel this way too. Maybe you hold back because you're afraid your ideas aren't technical enough.
You are enough. Having the right tools to grow doesn't make you less! It makes you braver. π
π§΅Everyone talks about the technical side of Claude. I want to talk about something different.
@claudeai makes me feel empowered. β¨
@claudeai Do I still feel like a fraud sometimes? Yes, honestly.
Every time I share something I get feedback that it could be done differently. That there's still so much to learn. But that feeling is smaller than it used to be. And that matters.
With Claude I feel like I have a buddy I can think out loud with. Ask questions. Explore ideas. Check if my thoughts are worth sharing.. without the fear of being judged.
I always felt less smart than others when it came to tech. Less intelligent. It's something I've been working on through the years, but it still haunts me from time to time.
I come from a non-technical background. One of the things that always set me apart was my different way of thinking about problems.. but I was also very afraid of exposing my thoughts, because I always felt I didn't know enough about the technical side to speak up.
@levelsio Although we strive to send only recyclable items to the bin, we accidentally include non-recyclable items or place recyclables in the wrong container (or items that contain both cardboard and plastic) which require sorting before they can be sent to the actual recycling plant.
@levelsio It's nice that you were doing this but please try to see all the facts as well.
Tratolixo is actually a waste management facility. Mixed garbage, plastic, and cardboard are intentionally collected together and later separated at the treatment or recycling plant.
@jenlooper You are amazing Jen! I have been following your work and I am a huge fan of yours. I know for sure that you will continue doing awesome things! ππ¦π¦π¦π¦π¦π¦π¦π¦π¦π¦π¦π¦π¦π¦
Awesome news today! @Cloudflare welcomes Chirantan "CJ" Desai as President of Product & Engineering to further accelerate the company's next phase of growth! π
https://t.co/20euLCxUK6
@Cloudflare London βοΈπ§‘
Last Seen Users on Sotwe
ΰΈΰΈΰΈΰΉΰΈ’ΰΉΰΈΰΈͺΰΈ²ΰΈ§ΰΈ£ΰΈΈΰΉΰΈΰΉΰΈ«ΰΈΰΉ ΰΈΰΈ§ΰΈ ΰΈΰΉΰΈ§ΰΈ
Seen from Thailand
PiZZAβοΈ
Seen from United States
Mommy Penelope
Seen from Mexico
Suka Ibu Ibu Tua
Seen from Indonesia
Mature TVπ 
Seen from United Kingdom
Hd Jav
Seen from Thailand
KONTLO OWDO
Seen from Indonesia
ayuH
Porn Oral creampie & Cum Face
Seen from Turkey
Sebastian Rios
Trends for you
Most Popular Users
Elon Musk
@elonmusk
240.1M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.6M followers
Cristiano Ronaldo
@cristiano
108.8M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.2M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.5M followers
KATY PERRY
@katyperry
86.7M followers
Taylor Swift
@taylorswift13
80.5M followers
Lady Gaga
@ladygaga
72.1M followers
Kim Kardashian
@kimkardashian
69.4M followers
YouTube
@youtube
68.6M followers
Virat Kohli
@imvkohli
68.5M followers
Bill Gates
@billgates
63.4M followers
The Ellen Show
@theellenshow
62.5M followers
CNN
@cnn
61.9M followers
Neymar Jr
@neymarjr
61M followers
X
@x
60.9M followers
CNN Breaking News
@cnnbrk
59.9M followers