I’ve been thinking about this exact workflow for quite some time. It just doesn’t make sense to read so much markdown. a html file that changes shape based on the type of work is the best output for collaborating with models. I think it’s even the key to manage parallel sessions
@KarimzadArsalan اتفاقا باید آدما رو هل داد کار بزرگ و مهم بکنن و زندگیشونو وقفش کنن. واسه من هیچی ترسناک تر از این نیست لحظات آخر زندگیم به این فکر کنم هیچ کار بدرد بخوری نکردم
@KarimzadArsalan اگه همه دنیا یذره کار میکردن این آقا توی رفاه همچین توییتی نمیزد. هدر دادن انرژی به واسطه زیادی کار کردن توی جایی که اهمیتی نداره بحث دیگس. ولی کار نکردن تشویق نداره.
@ajambrosino idk my experience aligns with what dwarkesh is saying. i asked codex to add something to my reminders and it was so confused by the save interaction that required you to click outside, that it gave up and ran a script
@remohammadi کل قضیه دروغه و سایت رو هم خود ایشون به نظر با ai جنریت کرده. همچنان اپ ها رو خارج از استور میشه نصب کرد فقط سخت تر شده و باید بری توی تنظیمات developer mode رو روشن کنی. و کل دنیا هم نیست، فعلا با سه چهار تا کشور آزمایشی شروع میکنن.
I feel like there’s a huge untapped market in fighting drugs. i don't see many startups taking this problem seriously while even from the surface level i can think of several promising angles to pursue.I’m just talking from vibes and observations,but it doesn’t seem incorrect lol
have heard from a few ppl now who've been rejected by anthropic for not recalling exact syntax
seems absurd at face value but remember Ant has one of the most talent dense applicant pools which permits them to be as absurd or nonsensical as they like & still be no worse off
My wife mentioned a nice private school over dinner this week
She said the campus was beautiful
I asked what's the tuition
She said we should look at it as an investment in him not a cost
I made a note
She said don't make a note
I said I always make notes
She said this isn't a deal
I said everything is a deal
She closed her eyes
She said we'd discuss it Saturday
I agreed
Saturday 7:02am
She came downstairs in her Saturday robe
Coffee in hand
I had my cargo shorts on
The dining room had been cleared
The projector was on
The analyst was at the head of the table
Quarter zip on, three iced coffees, a legal pad, and two laptops
He had been there since 6:44am
I texted him at 11:14pm Friday
The text said dining room 6:45am bring the model
He sent a thumbs up
My wife stopped in the doorway
She said what is this
I said you said you wanted to discuss it
She said this is not a discussion
I did not respond
She sat down anyway
The analyst stood
He said good morning ma'am
She did not respond
He sat back down
A printed deck in front of each seat
A fourth copy in case
Slide 1 Tuition Schedule
$38,500 per year
Thirteen years
$500,500 nominal
Before escalators
The school has raised tuition 4.2% per year for a decade
With escalators $648,000
My wife said okay
I said I'm not done
Slide 2 Opportunity Cost
Even before escalators
$38,500 invested annually
10% nominal return
S&P long-run average since 1928
By his eighteenth birthday $944,000
My wife said we can afford it
I said I know that's not the slide
Slide 3 Terminal Value at Age 65
$83 million
She was quiet
The analyst slid the sensitivity tables across the table
8% return $31 million
10% return $83 million
12% return $222 million
She did not look
She said this isn't about money
I said it's always about money
She said no it isn't
I said then what is it about
She did not answer
She said you can't put a dollar value on his teachers his classmates his environment
I said I can the analyst already did slide 6
He flipped to slide 6
She did not look
She said the school is the best in the city
I said best is a feeling
She said it produces the best students
I said the students were already the best before they got there
She said our son deserves it
I said our son deserves $83 million
My son walked in
He is five
Dinosaur pajamas
He looked at the projector
He looked at the open deck on the table
He looked at slide 3
He said are we modeling pre-tax or after-tax
The analyst opened a new tab
My wife looked at the ceiling
He said what's the discount rate
The analyst set down his pen
She closed her eyes
He said is this the same return assumption from the 529 conversation
The analyst stopped typing
He looked at me
I did not say anything
She stood up
Sat back down
He said dad can I help
I said yes
He pulled up a chair
The analyst handed him a printout
He started reading
My wife watched him read
She watched him for a long time
She said his name
He looked up
She said do you like school
He said the work is too easy and the kids don't ask questions
She did not respond
She looked at the ceiling
She walked out of the room
The analyst started packing up
He said should I follow up Monday sir
I said no follow up needed
He'll be fine
Sent from my iPhone
I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem.
As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)!
I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work.
It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results?
88ms => 1.5ms
150K allocs => ~500 allocs
Incredible right? Nope.
My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path.
This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput.
The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity.
Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.
these guys want you to spend sooo many tokens it's crazy. you can barely stop one agent from producing slop, let alone this many of them.
a few weeks ago they released another token hungry feature called agents view but i haven't seen anybody talk about it either
Excited to share our most powerful new Claude Code feature: dynamic workflows!
Mention "workflow" in a prompt and Claude will dynamically create an orchestration plan that it strictly follows, allowing you to confidently trust that every stage happens in the right order even across 100s of agents.
دم همه بچه هایی که این روزا واسه آزادی اینترنت تلاش کنن واقعا گرم. مارک و متین و ناشناس های دیگه پشت ابزار های مختلف. علی الخصوص یوسف قبادی عزیز که نمود جمله «بهار همیشه از یه گل شروع میشه» بود و حرکتی شروع کرد که هنوز ادامه داره. امیدوارم یه روز قدردانی مناسب بتونیم بکنیم ازشون
geohot is right on this. it took me time but i'm slowly reaching the same conclusion. stop the hype machine, you are ruining yourself
https://t.co/c7fN3msiZ6