Sarthak Upadhyay

owner of SaaS with zero users

[Sarthak Upadhyay @usarthak34]

@theo t3 code is so good that it made me do blasphemy of using guis for dev work

[Sarthak Upadhyay @usarthak34]

gpt dot slacking off

[Sarthak Upadhyay @usarthak34]

@thsottiaux https://t.co/SK8XWQUWNQ

[Yashaswi More @itsyashi24]

9 am: i can’t wait till bedtime

10 pm: i’ve always wanted to write my own operating system

[DHH @dhh]

Every developer needs an AI shed: An always-on machine running on their tailscale network where the majority of their herdr agents are running.

[Sarthak Upadhyay @usarthak34]

@dhh atleast we are backing to language wars taking a small break from ai model wars

[Sarthak Upadhyay @usarthak34]

@thsottiaux ai psychosis commence, no better motivator than upcoming random resets

[Sarthak Upadhyay @usarthak34]

@kentcdodds please get it done

[Sarthak Upadhyay @usarthak34]

@devagrawal09 its luna based, so still llm

[Sarthak Upadhyay @usarthak34]

@thekitze i counted grok bot, notion, jev, devin, last minute model upgrade

[timo @timo_rf]

Notion is crazy because how did they make it feel vibecoded before ai even existed

[nera 🦉 @nthrootofnera]

Finally, Apple has reached feature parity with GNOME

[Theo - t3.gg @theo]

Nothing in the world could have prepared me for the root cause of the performance issues with code highlighting in Claude.

STAR WARS EPISODE 5.5: EMDASHES STRIKE BACK

[Irushi @Im_IrushiK]

Give us a slow mode for Codex.

Something like /slow where it runs at half the speed but uses roughly half the usage. It would put less strain on OpenAI’s servers and maybe even make the 20x plan possible, right?

It’d be perfect for /goals too, just send a task before going to sleep and let it work overnight.

I’d happily trade speed for more usage @thsottiaux

[Theo - t3.gg @theo]

@RhysSullivan Thankfully it came right before I had to learn Effect

[Klaas @forgebitz]

"agi is here"

use cases:

- buy concert tickets
- draw a rocket
- list a table on ebay

these are not the problems i expected agi to solve

[ThePrimeagen @ThePrimeagen]

It is funny that it took gpt6 for people to realize why LLM benchmarks are terrible

[Sarthak Upadhyay @usarthak34]

@expo tears in my eyes…

[kitze 🛠️ tinkerer.club @thekitze]

devs: just make the product

designers: what if we pretended to make the product before we make the product