cho.sh
2,244 notes
Liked on XI made a mistake. When Jack and I decided to organize this $100K Hackathon, my biggest concern was cheating. Unlike a regular hackathon, everyone participates from home. And because the winner is whoever makes the most PROFIT (not revenue), there are so many ways to manipulate the numbers. So I added a $99 entry fee. One thing I’ve learned from building businesses is that people tend to be more committed when they pay for something. I thought it would filter out spam, attract serious builders, and make the competition fairer for everyone. But I completely missed the other side. 3 years ago, I was a living with my apps. Today, I’m financially free. My life changed so much that somewhere along the way, I lost perspective on what $99 means to someone else. For someone in India, someone struggling to pay their bills, or someone trying to make their first dollar online, $99 can be a lot of money. And those are exactly the people I want to help! I’ve spent years sharing what I’ve learned, reviewing random people’s landing pages, and organizing free meetups around the world. Not because there’s money to make, but because I genuinely love seeing people build things and succeed. And somehow, I was so focused on keeping cheaters out that I didn’t realize I was also keeping genuine builders out. That’s my mistake. So I’ve decided to make the $100K Hackathon completely FREE :) Everyone who already paid got a full refund. I’m still worried about cheating. That problem hasn’t disappeared, and Jack and I will have to figure out better ways to verify profits and keep the leaderboard fair. But that’s our problem to solve. Thank you to everyone who shared their thoughts. Sometimes you need people to remind you of things you’ve forgotten. I genuinely hope this hackathon changes someone’s life. ❤️Liked on XIt’s time to bring back Cafe CursorPosted on Xyo @pendev i can't live share edit a .pen file? it's the most needed featurePosted on XI'm coining a word "Agentsplaining" Agents condescendingly assuming the user don't know fuck and repeating the obviousReplied on X@jayhxmo @raycast Hard to explain. It's the small detailsPosted on X@raycast iOS keyboard is insanely good. Might resub Raycast pro just cuz of thisReplied on X@ishuagra02 I saw a theory that F5.2 is a post train of 5.1, but O5.5 is a distillation of F5.5(unreleased new pretrain) and thats why O5.5 > F5.2Liked on X@anaclumos don't know what is actually improved 👀Posted on Xam i the only one underimpressed with 5.2 fableReplied on X@bvvst great minds think alike https://t.co/YRFWhb1mcOLiked on XClaude Fable 5.2 is out and it's the perfect time to run this god-level prompt on your codebase: "I want you to audit our codebase, is anything here unnecessary, overly complicated in our current setup, or based on weak assumptions? Challenge them. - What can be deleted entirely? - What can be simplified now that unnecessary pieces are gone? Then make the changes. Prefer deleting over simplifying, simplifying over optimizing, and optimizing over automating. This product is being used by thousands of customers, do not cut any corners." This prompt is one I run often and leads to the best results.Replied on X@akshayadinesh19 @bot can we please BYOM for botsLiked on XTo be fair, the Chinese models have a much lower refusal rateLiked on XF*CK IT, im creating a library of AI slop indicators. my feed is full of taste larpers. stay tuned https://t.co/5Muv8nQRm3Liked on XJENSEN! THATS NOT WHAT WE MEANT BY CHINESE MODELS!!!!!!!Liked on Xmy parents had to declare bankruptcy when I was a kid, so they had every reason to pressure me towards a more stable career path instead, they were so patient with me, even as i failed startup after startup for years so getting to tell my mom that everything turned out okay was a really special moment :) for those who can't read Korean, her first message roughly translates to: "Really!!! Congratulations my son. So much :') Thank you God!" i know I've been posting about my exit for like a week now, but it really is a big deal for me and my family! i'll share more about how this all happened and some tactical advice later this week, but for now i'm just riding out all the emotions to quote my mom, thank you God!!!!Liked on X@thefarmers_Dog it stands for Egg GzampleLiked on X🦍 Introducing Memorilla: memory as a modality for LLMs Memorilla turns everything a frozen LLM needs to remember into just 16 memory embeddings ⚡ It uses up to 4,212× fewer tokens and is 27× faster than full context inference while more accurate 🎯 Pushes the Pareto frontier over RAG and agentic memory in personalization, long-document and knowledge QA A thread 🧵:Liked on XThere's a huge product opportunity downstream of Tailscale etc too. At @tldraw we've started designing for "high trust networks" and it's been a beautiful thing. 1. Features that would be a nightmare on the internet are okay on my computer and mostly okay on private networks. Websites that execute user-generated scripts, control production systems, allow for users to send desktop notifications, spend tokens, or directly prompt my agent. Crazy stuff that would only make sense if everyone was in a committed polycule. 2. When everyone on the server can be trusted to have _external_ reasons for good behavior (eg keeping their job, or maintaining friends, family, church, mafia org), the software can be designed in a default social way. Most apps default to isolation, low horizontal visibility, highly restricted collaboration. Makes sense if the social contracts are inside of the app, but if you can trust that they live outside of the app then you can get wild. Example being small group chat names as an emergent comedy phenomenon because anyone in the group can change the name. 3. This can work for commercial products, too, not just internal stuff. Security matters more than ever but the way we've seen that manifest is that more companies are more confident in their own solutions than anything we could provide, to the point where owning data and access is a better value proposition than having it managed. Always has been true for big companies but now even small companies can get a good secure network set up pretty easily, and the hooks we need to build are easy enough. tldraw offline got us started down this road (and shout out to @pendev for first introducing me to the idea of desktop + mcp). We've been bringing that product to private networks and it's been exciting to see how much we can get away with. Keep an eye outReplied on X@saradu birds eye viewLiked on XApplications close in 2 days!! If you have a cool bio idea, and $5-10k will go a long way for you, please apply!!! https://t.co/NCvmrNC53cLiked on XWe've been early adopters of Rust since 2018 and a lot of our infra, voice tech, and even some of the current client is already Rust, the holy grail was getting the whole client there. That means Electron goes away, and so does React Native, mobile keeps native UI but shares app code with desktop via Rust. We hope to get it into testing with users soon™. (And it's not Tauri, it's GPUI, so good guess everyone.) Alright, back to staring at the WoW Forever login screen.Reposted on XOh boy. https://t.co/X7SSskGuGvLiked on XRIP .si domain squatters
Limitless Day One Review

Limitless Day One Review

twitter.com/anaclumos/status/1780033289992204540

@limitlessai day one review

Today I spoke for 2 hours with @jameszhou02, a really good enginifounder.

Natrually I had to give @limitlessai a spin, as an avid @RewindAI user and @dsiroker fanboy.

73965E

Some bugs first:

The summary was surprisingly really good, but missed some key points.

For example, we discussed whether big tech exists. will help found a startup.

James and I had slightly different perspectives (which we both respect), but our 20-minute discussion was simplified into this one block.

576823

It misunderstood some jargon and didn't even understand popular jargon like ChatGPT.

It'd be great if I could add personal Jargons in a user-friendly way.

p.s. The companies transcribed wrong here are "Moloco" and "Grammarly"

239EE1

324D32

Also a bug in running RAG on the same recording clip over and over.

We only talked about Grammarly's team selection for a couple of minutes, but at least 30+ sections are on Grammarly and Personal Agency.

We also did not talk about game-related projects.

TIL there's a city named Brammerton

C68C62

The transcript tab is not only non-chronological, but also mixed up. It starts with a sentence at 101m, then jumps to one at 34m.

B91AA5

22D369

I must acknowledge that the app is surprisingly polished for a day-one product, and I'll daily drive this.

Ideally, I hope Limitless and Rewind merge into 1 product, because now my data is split across tools.

I even preordered the Pendant last year, guess I made a good bet!

9A10B9

If that ever happens, it'll also be interesting to see how Limitless handles the data migration with Rewind.

Not many service updates require you to upload 100 gigs of videos.

I still trust the Limitless team that they'll make it as smooth as possible

AEB7B5

I have a huge trust in Rewind because they didn't just jump on a hype train.

They actually thought of a good use case of AI:

Eidetic Memory Devices.

cho.sh/r/ECF81E

Humans don't need $700 pins to shoot lasers or replace your phone.

We don't need pins to ask about the weather or how tall the Empire State Building is.

That was Humane's mistake. They didn't think about what "additional value" they should/could bring.

FB7F8B

We need pins to get eidetic memory. Nothing more.

That's the additional value these new form factors should/could bring.

And I think @dsiroker is one of the very few people who actually understands this.

I am also really excited about how Limitless will change , or Digital Gardening, on the web.

Notable tools in this space is @RoamResearch and @obsdmd.

8BEE60

I think Memexing is the most "practical" way to achieve eidetic memory, so far.

I still don't fully see how AI will help Memexing; all implementations so far have just made my memory worse

It's cuz if you don't think in your own words, you typically forget things really quickly

But one thing is for sure is that...

We will either

① find a sweet spot in between "brain-busywork makes you remember" and "go full on brain-autopilot"

② or come up with an ingenious UX to both let AI do the brain-busy work and also make us remember things better.

And I'm betting that Limitless would do one of the two, or at least help us get there.

They know the problem they should solve.

I want to close my thread with a quote from Ted Chiang that addresses the social implications of remembering everything.

cho.sh/r/6C8C05#the-t…

"As someone whose identity was built on organic memory, I'm threatened by the prospect of removing subjectivity from our recall of events. I used to think it could be valuable for individuals to tell stories about themselves, valuable in a way that it couldn't be for cultures, but I'm a product of my time, and times change.

We can't prevent the adoption of digital memory any more than oral cultures could stop the arrival of literacy, so the best I can do is look for something positive in it. And I think I've found the real benefit of digital memory. The point is not to prove you were right; the point is to admit you were wrong.

Digital memory will not stop us from telling stories about ourselves. As I said earlier, we are made of stories, and nothing can change that.

What digital memory will do is change those stories from fabulations that emphasize our best acts and elide our worst, into ones that--I hope--acknowledge our fallibility and make us less judgmental about the fallibility of others."

-- The Truth of Fact, the Truth of Feeling, Ted Chiang (2018)

Backlinks1