Hello World

Burner acct for a media exec interested in too much. (RTs= Bookmarks/Reading Reminders to Self. Not my actual views.)
Masked Email: [email protected]

[Anshu @anshuc]

I learned this the hard way: do NOT use SwiftUI if you want your app to look and feel amazing. At least when coding with AI. (sorry, Apple colleagues reading this 😅)

I'm sharing my process vibe coding this calorie tracker. I get a lot of questions about the fluid transition in the video. Here's the whole story.

Initially, Claude built the grid with SwiftUI. It was quick and easy, and looked good! But the transition to the day view was a boring navigation push/pop. No fun. I wanted something custom.

I asked Claude to make it a fluid transition that remaps the food tiles from their source to destination positions. All hell broke loose.

Claude tried a bunch of horrible things. Initially it used matched geometry effects, which worked OK but didn't lend themselves well to gesture-driven animations. So it resorted to SwiftUI preference keys + geometry readers to figure out the source and destination positions and calculate the interpolated position based on gesture progress, coordinating across grid and day views. But this meant it had to write a custom layout because it couldn't reposition tiles inside the native SwiftUI grid. And it had to do an awkward handoff between views, which always created ugly pops or jumps. And don't get me started on trying to put it on a bouncy spring, that only made the math 10x buggier.

Fortunately, Claude Fable was smart enough to see that this was becoming a disaster (and discover most of the issues itself, in the simulator), so it pivoted away from SwiftUI. Opus might not be so wise, so you'll have to pay attention and intervene.

Ultimately, it rewrote it in plain UIKit and everything turned out great. After that, we moved from 2D images to 3D assets, which introduced a new set of performance challenges and yet another rewrite to a single Metal layer, which is what you see below. I can write more about the 2D-to-3D saga if anyone's interested.

If I were to do it again, I'd just say "Don't use SwiftUI" from the very first prompt, and save a few hours of headaches. SwiftUI can be amazing for a human iterating directly in code. But agents don't benefit from any of its advantages. Plus, agents have seen decades of UIKit training data, so they're great at writing it, and it's far more flexible.

Here's hoping we see more agent-friendly iterations of SwiftUI in the future. Till then, I'm probably going to avoid it.

[Madhav Chanchani @madhavchanchani]

Polymarket created a clone website so creators could fake winning trades, according to WSJ.

It also used an agency to promote videos showing how easily insider trading could be carried out on the platform.

[Brett @BrettFromDJ]

Released by popular demand...

GatherOS now automatically syncs your Instagram bookmarks in addition to X (Twitter).

[Jakub Krehel @jakubkrehel]

It’s incredible that /make-interfaces-feel-better has already been installed more than 30,000 times.

It contains a lot of tips that make interfaces feel better, across UI, animations, performance and more.

npx skills add jakubkrehel/make-interfaces-feel-better

[Neil Mehta @neilmhta]

NEW investigation for @WSJ:

- Polymarket is paying scores of offshore clippers to quietly promote its international exchange in the U.S. (though it’s banned from letting Americans trade on the platform)
- Polymarket made dummy websites mirroring its real site, then paid creators to use the fake site and pretend to win thousands.
- Creators altered headlines and used outdated footage to imply they won bets—even when they often lost
- Polymarket paid Adin Ross multiple millions to promote the site

All that and more in my latest story with @ByKLong @ceostroff @brenna__smith

[Jaynit @jaynitx]

Conor Neill on why luck is not random and how to deliberately get more of it:

1. Luck flows through people and travels by conversation. James Clear's framing: keep talking to the same people, keep finding the same opportunities. start talking to new people, start finding new opportunities. If you want different luck, start walking into different rooms. The people you have access to determine the opportunities that reach you. This is not a metaphor. It is mechanics.

2. What separates successful people from unsuccessful ones is not the amount of luck they receive. It is return on luck. Jim Collins's idea: when a luck event presents itself, what do you do with it. Most people get roughly similar amounts of lucky moments. The difference is who is prepared and paying attention when they arrive.

3. A careers advisor in Spain gave one piece of advice that changed everything: meet one new person every week. For 25 years, the speaker kept a slot in his calendar every single week for a coffee with someone new. almost every significant opportunity in his life, his teaching role, his business, came through a single individual and a conversation. The math on one new person per week over 25 years is staggering.

4. When you meet someone new, you are starting at number 21 on their list of priorities. Dan Sullivan's framework: they have at least 20 things more important than talking to you. If you spend the conversation talking about yourself, your goals, what you want, you drop from 21 to 30 to 50 and fall off the list entirely. If you ask about them, their goals, what brought them there, you move up. Most good people, if you explore who they are, will then explore who you are. That is how a real conversation opens.

5. Luck surface area is a size you can control. The more people you meet and the more genuine conversations you have, the larger the surface through which luck can reach you. same people, same conversations, same luck. new people, new conversations, new luck. It is that simple, and most people never deliberately expand it.

[Patrick OShaughnessy @patrick_oshag]

I've gotten a lot of texts saying they loved how Kareem defines courage and risk in this episode, so sharing it in full:

"If you look at old republics, they would have statues for concepts like courage or integrity or justice, we’ve forgotten these abstract ideas matter when you’re building a company.

Capitalism rewards risk more than anything else. A lot of people think it's meritocracy, or hard work.

There are a lot of people working really hard and not making a lot of money. It doesn't just reward skill either.

You can be eating a sword or juggling and not make as much as someone doing a YouTube video.

A lot of people think they're taking risks but aren't taking real risks. I talked to one founder who went to a good school, then YC, and he was telling me about his company.

He said, we serve sales and we serve recruiting. I said, you have to pick one. That's where you actually provide value, in committing yourself to serving some group of people in some specific way.

My definition of risk is that you genuinely don't know what's going to happen, so you're going to discover something new. And it needs to be coupled with a high potential for shame.

That's when you're genuinely about to discover something new, and that's when you can take real risk.

And to do that, you then need to have many traits. One of them is courage.

When you couple risk and courage, the next part is commitment. You actually need to follow through to see what ends up happening.

You can't just quit in the beginning. If we see somebody has star potential, we stay with it way longer than most."

[Nyra @Nyra_nx]

Claude can now pull live data from 135,000,000 YouTube channels.

Most creators are still paying $200 a month for analytics tools that do less.

Here’s the part nobody’s using.

Without the connector, Claude guesses. It gives you generic advice it could’ve written in 2023.

With it, Claude reads real-time data across 135M channels — and tells you exactly why your last video bled viewers at second 14.

Setup takes under 2 minutes:

→ Copy the connector URL (link in reply)
→ Open Claude, click Customize
→ Go to Connectors, click Add custom connector
→ Paste the URL, click Add
→ Done

Now you can run prompts a $2,000 consultant charges for:

“What’s trending in my niche right now?”
It pulls live topics climbing in your exact category — not last month’s leftovers.

“Why did people click away from my last video?”
It breaks down the drop-off, second by second, against channels that retained.

“Rewrite my title to match the top 10 performers in my niche this week.”
It studies what’s actually working today and gives you 5 options.

The math is simple.

A creator with 10,000 subscribers who lifts average view duration from 40% to 55% can 3x their watch time without a single new video. That’s the difference between $400 a month and $1,400 a month on the same uploads.

The data was always there. 135M channels, every retention curve, every title that worked. You just couldn’t read it.

Now Claude reads it for you in 30 seconds.

Most people will scroll past this and keep guessing. 7,000 will set it up tonight and stop guessing forever.

The window on “nobody knows this yet” closes fast.

[Hello World @HelloWo40063049]

@TwinkTheory is this PILLION (2026)

[Olivia Moore @omooretweets]

ChatGPT Pulse was an early attempt at what feels like one of the most important problems in consumer AI

How can you use context on someone to do useful things for them proactively?

This is trickier than it sounds - some of my thoughts as a former Pulse user:

1. Being able to separate context is crucial. It felt confusing to get a Pulse that combined personal things discussed with ChatGPT with stuff from my calendar or research areas I was interested in. I don’t know if the answer here is separate summaries or just a more clear way to blend / prioritize between them

2. How you build info density matters. Access to my calendar, email, and chats is helpful - what if it could access my Granola notes? Or plug into my Goodreads account? The more connectors the better for a product like this, IMO. As we’ve seen recently with products like @interaction and @tomo, existing messaging channels (iMessage, WhatsApp) remain very sticky and are a natural channel to drive engagement

3. Suggesting workflows is helpful - but it needs to be customized. My usage of Pulse was somewhat sparse as it didn’t seem to have a great sense of what to surface to me when (and how to one-click action it!) On the other hand, I don’t think many users will build scheduled tasks if it takes anything more than a chat to set them up…this feels like both a model and harness problem to customize correctly per user

I’m very bullish on the future of products in this space - and with working agents I think we’ll see a 10x product here soon. Pulse had real moments of brilliance - when something is surfaced at the right time it can feel magical!

[Peter Yang @petergyang]

You can now make videos like this using HTML.

I didn’t believe it at first until the HyperFrames team showed me how they do it directly in Codex and Claude Code.

Best of all, the tool is 100% free and open source.

But you need to learn the right workflows to make the videos look great - including generating a frame.md, storyboards, and more.

📌 Subscribe to get our full tutorial tomorrow: https://t.co/NSTj7ijxE0

[Boring_Business @BoringBiz_]

Probably the realest thing I have heard Chamath say

"Possessions are BS. They are worthless. They are a sign of insecurity, a rampant ego, and an unsettled mind. And that is okay if you are going to be a mid."

[Patrick OShaughnessy @patrick_oshag]

One of my favorites from the last two years

[Hello World @HelloWo40063049]

@realDonaldTrump We can just pronounce it N. I. C. E. or NICK-EE or NEESE or anything else to troll you back

[Esan @esandurrani]

we purchase new AI tools every week

but half the team doesn’t know how to use them

So I built an agent that:
- uses Exa AI to research the product
- builds a course
- screenshare with an AI tutor

here's how I taught my team how to use claude code:
https://t.co/ShJjVdnk40

[Gohar @gohrabbas]

launch videos are now non-negotiable

[Lenny Rachitsky @lennysan]

There's a very good reason @evanspiegel is investing so heavily in hardware.

Everything Snap has built over the last 15 years has been copied.

His thesis is that as AI makes writing software easier and easier, hardware will be one of the only remaining durable moats.

[Rohan @dvvdle]

Started a new company.

This is a software and creative venture company. We will build beautiful + viral consumer software and products.

Say hi to Internet! https://t.co/5D0S0ULJZt 📁

[Justine Moore @venturetwins]

I am crying of laughter at the Zoomers trolling AI interviewers

[Zephyr @Zephyr_hg]

Sam Altman, OpenAI's CEO:

"Suddenly they can do in an afternoon what would have taken two years."

In a 47-minute TED conversation he lays out where that speed goes next, from coding to every kind of knowledge work.

The catch he doesn't spell out: that speed is free to everyone now. What you do with it is the skill almost nobody has built yet.

Watch the talk, then read the article below for what that skill actually is.

Save this one.