Founders

can’t believe i have no lights on my dashboard anymore

can’t make it work on anything i need

so much but sad to not have a feedback mechanism

Added a small printer that prints anything by anyone from this web page! https://korshakov.com/contacts

will be here today https://luma.com/ezto1ndf

this is surprisingly same graph as vibecoded apps

Well experiment is terrific success: https://happy.engineering/streams/ It is very performant, very heavily tested by multiple models and API and devex is exactly what i needed. Vibecoded test with a chat and it works almost perfectly

Trying to implement childhood dream, what if it will solve this ethernal pain once and for all?

yet another thing that i figured out months ago and decided not to ship: https://x.com/_catwu/status/2060054180379689074?s=46&t=A1zE0kfmZyf1QVe55CmQQA

ideas i did pass: 1) coding assistants, coding harnesses (now could have been one of the top easily or at least have a name) 2) vector databases (it turns out most of them were indeed shit except turbopuffer) 3) compact nuclear reactors (guess what’s the next way in energy in us?) 4) home management - literally take 3d scan of a home enumerate everything autistically and vendor contractors and sell as subscription. (guess what was recently launched in bay area?) ideas i did try: uber for dogs

There is an infinite list of apps i want reimplemented: 1) Plex - slow, overheats Apple TV, stutters, not smart enought to classify movies, super weird closed source software 2) Todo apps - most of them are not focused for thought where you sort stuff around and highlights important ect etc, still havent found good one 3) Better notion - simpler, but not lacking and high perfromant, including the native mobile apps not html abomination 4) Calendar app - all of them was acquired and killed nothing on the market at all 5) "company/home brain" - not some half-assed implementation that everyone have 6) Car Tracking apps, RaceCrono is good but it haven't changed in last 10 years 7) GoPro software is dog shit to sync 😍 Personal dropbox or something that doesnt make me depend on random cloud and wont be wiped using some worm 9) Home automation, including parsing video feeds and smart rules, can something detect that i woke up instantly? 10) Managed AI where all this is interconnected, not running claude in the loop and not insanity of openclaw 11) Simple document app, like quip (that would be turned off soon!) - simpler than google docs with comments etc etc, it is like medium but slightly better 12) Finance apps - how would you build and project and estimate your personal/family financials? there are only pre-ai tools like monarch which is barely useful 13) Self-organizing document app (mix of 3 and 8 and 11?) - upload doc and it would be stored somewhere and can't be deleted, extracted structurally and ready to use by me and agents. Something else probably needed too. Where the fuck vibecoders that would build all this that is plesant to use?

I did two very long experiments with GPT-5.5 xhigh fast, one failed completely, another one succeeded wondefully. I had a task 2 years ago and it was very hard task - i needed to boot android emulators as EC2 instances or as some VM, but i needed it to be safe and contrained, not some forked QEMU with disabled security. There is still no solution for this - you have to build something yourself, i have asked GPT to boot android in Apple Hypervisor (write swift app to use this api!) and show me screenshot of it and give me a web ui to control it remotely. It implemented it perfectly, it took vanila AOSP build, created a 30+ patch files, build a dockerfile with all scripts to build an image and then booted it on mac. Then i asked to use vanila QEMU and it succeeded too. Then i asked it to benchmark GPU against host, it succeeded too. Then i asked it to make it secure, thats where my token limit ended, but i assume it would be still successful. Second task is to build an AI runtime. I need a some unified way to run agents that WONT require me writing code, but i still can configure system nicely. That would work with API and with Subscriptions, that would have different sandboxing mechanisms, etc etc. This task failed. It failed because it did work on non-latest main (i forgot to pull) and it built some very very simplified version and completely wrong. I have asked then to pull the main and thats where everything become a huge mess. So far i am impressed, didn do similar test for Opus tho, curious how it will perform.

blown up all codex tokens: pay for more or switch to claude for a weekend?

i am still looking to find what’s wrong in my reasoning about building products/companies. i learned some in recent days: 1) i reject many ideas because i can build them in a day, but absolutely no one can or want to do the same, even simplest things 2) i feel that challenging ideas is not a way to make friends - people in sf are consistently agreeing to each other and not sharing anything direct with strangers, while this is usually a reason something collapsed spectacularly - it is not a basis for Californian people

I have seen one movie - Obsession and it was like the best horror or even one of the best movies at all i have seen in a while, they now printing infinite money, opening weekend they made 16m$ on 750k budget, yesterday they made double of amount made by Mortal Kombat. I have a special spot when some small authentic teams win like this.

Sometimes i like the models, they do crazy things. I was building a small shim for Amazon Bedrock inference and it didnt work for something, Codex decided to find where claude is installed went to its folder, grepped its compiled js files and found how claude code does this and replicated. Zero prompting.

first in my bloodline to have MRR

Very nicely written text, haven’t seen much better long form posts on X https://x.com/jayagup10/status/2052870394093408558