YAAK

@levelsio That's great! Thanks for sharing. Which model was used? Are you fixed on Opus or change the model depending on the task? Would be nice to have a picture of the costs too.

This week I decided to just permanently switch to running Claude Code on the server mostly on bypass permissions mode: c() { IS_SANDBOX=1 claude --dangerously-skip-permissions "$@"; } And for the first time in my life I think I've actually managed to outrun my todo list What happened is I simply blasted through my to do list of features I had to build and bugs I had to fix I've never shipped so fast and Claude Code almost made no mistakes, and when it did it they were tiny that weren't fatal (important because I'm mostly working on the server in production now) Before I was always known to ship fast (also because I always work alone) but while I shipped new things would always build up on my features/bug board (my users can submit them there) But this is the first week where I've been fast enough to outrun them The board is actually empty! As other people have written on here the real bottleneck is becoming myself and my creativity, not how fast I can ship. Because I think I ship faster now than I can come up with new ideas, or maybe my brain will adjust to this new speed (probably) Also I feel another limit is becoming my own mental context window, as in how many things, features, bugs, projects, I can keep in my mind in parallel while building on all of them. It's a lot and I haven't reached that limit yet but I feel I might be close I also noticed that you start going really fast the more you let it just go loose, before I was slow because I didn't trust it and I was scared it would destroy my code, now I just let it go. As @karpathy wrote, things feel like they've changed a lot around December last year when models became good enough to really code with and I feel the same When I see other friends code with Claude Code I often notice they're slow because they still check everything, which is good of course, but I feel the better way would be to create some tests and just let it run freely and see if it can pass those For me the tests are mostly just me checking out if the new feature on the site works or not, and in 99% cases it just does, and then I ask it to improve it further Because I run Claude Code on the server in production, I don't have to wait for deployment anymore (although that took only 3 seconds anyway before, that still adds up), now it's wait for it to be done coding, I refresh the site and I test it, that feedback loop is how I work and it's made me WAY faster Anyway here's what I did this week and the majority of these things were requested by people on the bug board, I'd say this is about 10x my normal output: 📸 Photo AI - Built new image viewer and mobile image viewer - Added batch remix, multi-photo import, filtering by model in gallery - Security overhaul: phased out insecure ?hash= login, migrated to session tokens - Fixed Google login loop, multi-model selection, talking scripts - Added custom audio upload for talking videos - Created dynamic model selector from server endpoint 🏡 Interior AI - Revived [ Add furniture ] feature (started 6 months ago, image models now good enough) - Added custom style upload for redesigns - Built own Gaussian Splat viewer for 3D - Made /remove_bg endpoint for furniture backgrounds - Migrated 3D walkthrough to new World Labs API - Added .skp file support, paint color masking, empty room button 🎒 Nomads - Launched weekly AI-generated newsletter from chat - Built profile edit modal, moved profile editing from /settings to profile page - Added TikTok/YouTube links, status bar, server-side API tracking - Added hundreds of new profile tags and traits - Fixed timezone filters, broken links, user avatars 🗺️ Hoodmaps - Revived write mode (before was only read for last few years because db was rekt) - Built heatmap mode using sentiment-scored tags (50K+ tags) - Fixed root cause: tags not entering DB due to wrong PRAGMA (should be WAL) - Added good/bad area detection with admin grid controls - Set up Claude Code Telegram bot for live changes - Enabled CF cache, fixed health check, fixed Brussels 📕 MAKE book - Built auto ePub/PDF generator cron worker - Added dynamic generation with personal customer watermarks - Added image compression for file size 💾 Pieter .com - Added Wikipedia text-only reader for Kindle - Exploring Windows 3.11 emulator using v86 (to replace Em-DOSBox) - Added product recommendations on homepage - Installed Wall Street Raider (1986) 👩‍💻 Remote OK - Installed Chatbase AI customer support bot - Added "report not remote" link on job posts 🏨 Hotelist (3 todos) - Fixed hotel URLs and city range bugs - Added iron amenity

@elonmusk @grok How much mass can be transferred from Earth to the Moon without significantly altering the Moon's orbit?

For those unaware, SpaceX has already shifted focus to building a self-growing city on the Moon, as we can potentially achieve that in less than 10 years, whereas Mars would take 20+ years. The mission of SpaceX remains the same: extend consciousness and life as we know it to the stars. It is only possible to travel to Mars when the planets align every 26 months (six month trip time), whereas we can launch to the Moon every 10 days (2 day trip time). This means we can iterate much faster to complete a Moon city than a Mars city. That said, SpaceX will also strive to build a Mars city and begin doing so in about 5 to 7 years, but the overriding priority is securing the future of civilization and the Moon is faster.

True human-level intelligence demands continuous learning that can actively override its pre-training. It relies on a critical balance: the ability to forget the noise so it doesn't overfit, while remembering enough to stay useful, much like how the human brain changes during sleep. Ultimately, it needs to abstract vast amounts of data analysis into a distinct 'feeling' or intuition. We don't see this ability in current frontier models yet. They are only a fraction of what human intelligence is. However, that doesn't mean these tools won't automate tasks that are currently handled by humans. Even without true intuition, these models are capable enough to automate a vast number of tasks. The market demand for routine or less creative "cognitive labor" is falling. Humans in the middle of the intelligence spectrum are being outcompeted by "low-level artificial intelligence at scale". In an economy that is already tightening, first, we will see declining incomes for the less adaptable, followed rapidly by their total unemployment. In this assumed future, isn't the winner the one who owns the "low-level AI at scale" and the loser the one who competes with it?

Was "The Matrix" just a movie, or a preview?💊 Don't you feel like the scene in The Matrix, where Neo gets plugged in and instantly learns martial arts, is basically what we’re watching happen with LLMs right now? We plug all the documented human data into these models, and suddenly they "know" things and are able to answer our questions. Being able to learn everything has always been a dream. Just absorbing every book, every paper, every piece of documented history. But obviously, that’s impossible for a human brain (at least mine) and not even possible in one lifetime (at least not yet!). So, maybe rather than trying to learn it all individually, the real dream is to build a "Mind" that can hold all that knowledge. That leads to a hard question: "If you had access to a mind that knew everything... what would you actually do with it?" And no, I'm not referring to "the answer to the ultimate question of life, the universe, and everything" I am genuinely curious what you would actually do with it. We talk a lot about the technology, but not enough about the purpose. What would be your first request to "The Construct"? "Lots of guns" or "how to fold a protein 🧬"? #AI #TheMatrix #curiosity #future #technology

Verifying myself: I am yaak on Keybase.io. KY7b-HT-yRx8aNvNVF_dkiNSJ4XzChkqizKI / keybase.io/yaak/sigs/KY7b…