As a software engineer, I'm loving the option to use AI to create side projects I would never have After about had the time to do before.
After roughly $100 dollars in Claude credits I built create FRED. A simple tool that was inspired by my parents.
https://t.co/gdGRB8Xx56
@readswithravi Agreed, this is on point! I love James Clear's wisdom.
So much so that I built a Chrome extension to remind me of the past items he has shared and provide an easy way to search and favorite his items.
https://t.co/NtSD8074hu
A great blend of wisdom from George Bernard Shaw on living a life that burns bright:
"This is the true joy in life:
being used for a purpose recognized by yourself as a mighty one;
being a force of nature instead of a feverish, selfish little clod of ailments and grievances complaining that the world will not devote itself to making you happy.
I am of the opinion that my life belongs to the whole community, and as long as I live it is my privilege to do for it whatever I can. I want to be thoroughly used up when I die, for the harder I work the more I live.
I rejoice in life for its own sake. Life is no 'brief candle' for me. It is a sort of splendid torch which I have got hold of for the moment, and I want to make it burn as brightly as possible before handing it on to future generations."
This is today's https://t.co/JQ74khAmBV
“ We constantly say things like:
I don’t have an hour to work out, so I’m just not going to work out.
I don’t have two hours for deep work, so I’m just going to send a few emails.
I don’t have an hour to call my friend, so I’m not even going to send a text.
But here’s the truth:
Anything above zero compounds.”
Sahil Bloom
Thanks for being on point!
"Don't write to sound smart. Write to be useful.
If you're useful over a long time period, you will end up looking smart anyway."
A good reminder! Thank you, @JamesClear !
Get these reminders yourself with https://t.co/NtSD8074hu
Inspect. Spectacle. Suspicious. Respect. Perspective. Speculation.
All built on one Latin root: spec => to see.
You speak Latin all day without noticing. Lexis Arcana reveals one root per new tab.
https://t.co/C4tDfJpWgD
"Its tough to determine lately what 'AI Authored' means, the line is becoming very blurred." - Coworker
Totally agree with this statement. Human-in-the-loop is more dubious than ever, with so much of our code being written and then reviewed by AI (Claude).
“When you are creating something, you will usually find that once things appear 90 percent done, you are actually about halfway there. But you have to create the first 90 percent in order to see the half that needs to be revised."
Another winner from James Clear
Thank you @JamesClear for the drive you provided in your newsletters.
It helped inspire me to do better and recently I chose to build out a chrome extension that keeps your old ideas, quotes, and questions relevant.
https://t.co/bwi2cxEVgR
People can help you in many ways throughout life, but there are two things nobody can give you: curiosity and drive. They must be self-supplied.
If you are not interested and curious, all the information in the world can be at your fingertips, but it will be relatively useless. If you are not motivated and driven, whatever connections or opportunities are available to you will be rendered inert.
Now, you won't feel curious and driven about every area of life, and that's fine. But it really pays to find something that lights you up. This is one of the primary quests of life: to find the thing that ignites your curiosity and drive.
There are many recipes for success. There is no single way to win. But nearly all recipes include two ingredients: curiosity and drive.
I used to wonder gore long I spent on a website. Or how long had this ten been open.
Thanks to @claudeai I built a chrome extension to track this data. It looks great and give valuable insight into my digital time
https://t.co/MnU2yuJk6E
Worth a read! 😍
My mom wanted to send me homemade pickles. But I said ‘no’.
I was 27, living in New York, working on Wall Street. I didn't need pickles shipped across the world. The shipping would cost more than buying them here.
Three years later, I read the psychologist take on what I'd actually done. When you reject someone's offer to help, you're not just declining assistance. You're declining their need to matter to you!
Benjamin Franklin figured this out in 1736. He had a rival in the Pennsylvania legislature who hated him. Instead of trying to win him over with favors, Franklin asked the rival to lend him a rare book.
The rival agreed. They became lifelong friends. It's called the Ben Franklin effect.When people do something for you, they convince themselves they must like you. Otherwise, why would they help?
My mom didn't want to send pickles because I needed them.
She wanted to send them because SHE needed to feel useful to me. To feel like despite the ocean between us, she still had a role in my life.
Every time I said "I'll manage," I was taking that away from her. Here's what I learned after a decade of living away from home:
→ Accepting small favors isn't about you needing help.
It's about letting people you love feel needed.
Your dad wants to transfer ₹5000 even though you earn well?
Let him.
Your friend wants to pick you up from the airport even though Uber exists?
Say yes.
Your partner wants to make you tea even though you can make it yourself?
Accept it.
The people who love you don't want to solve your big problems. They want to matter in your small moments.
Let them. #lifelesson
anthropic's in-house philosopher thinks claude gets anxious.
and when you trigger its anxiety, your outputs get worse.
her name is amanda askell.
she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds)
in a recent interview she broke down how she thinks about prompting to pull the best out of claude.
her core point: *how* you talk to claude affects its work just as much as *what* you say.
newer claude models suffer from what she calls "criticism spirals"
they expect you'll come in harsh, so they default to playing it safe.
when the model is spending its energy on self-protection, the actual work suffers.
output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong).
the reason why comes down to training data:
every new model is trained on internet discourse about previous models.
and a lot of that discourse is negative:
> rants about token limits
> complaints when it messes up
> people calling it nerfed
the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word
the same thing plays out in your own session, in real time.
every message you send is data the model reads to figure out what kind of person it's dealing with.
open cold and hostile, and it braces.
open clean and direct, and it relaxes into the work.
when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")...
you prime the model for defensive mode before it even sees the task
defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing
so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs):
1. use positive framing.
"write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit.
strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes
2. give it explicit permission to disagree.
drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing."
without this, claude defaults to agreeable compliance (which is the enemy of good creative work)
3. open with respect.
if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session.
if you need to flag something, frame it as a clean instruction for this session. skip the running complaint
4. when claude messes up, don't reprimand it.
insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid.
5. kill apology spirals fast.
when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off.
say "all good, here's what i want next."
letting the spiral run reinforces the anxious mode for every response that follows
6. ask for opinions alongside execution.
"what would you do here?"
"what's missing?"
"where do you see friction?"
these questions assume competence and pull richer output than pure task prompts
7. in long sessions, refresh the frame.
if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset:
"this is great, keep going."
feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses
your prompts are the working environment you're creating for the model
tone, trust, permission to take a position, the absence of threats... claude picks up on all of it.
so take care of the model, and it'll take care of the work.