Shekhar Upadhaya
927 posts

Shekhar Upadhaya
@_usernamed_
Product | Tech | Design
Tokyo Beigetreten Mayıs 2022
265 Folgt363 Follower

I recreated @emilkowalski's beautiful react spring cards for Linear from scratch using Claude, just used react and CSS. It took me some time to get right, but shows you can get a similar effect with a few good prompts. 🤌🏼
English
Shekhar Upadhaya retweetet

@andrewchen We might as well see single-agent unicorns from AI. AI doesn’t just scale founders.
English

AI will make teenage billionaires a thing
why? People have long argued that we'll see more 1-person unicorns from AI, as the tools allow a singular visionary to scale themselves. That's obvious.
But it also follows that AI software will be created and run mostly by young people, and billions will be made in the process
AI also makes coding and product building as easy as making videos or posting a photo. The data says that the time rich (rather than money rich) dominate internet usage -- after all, they have more time to consume, and more time to create. Because the time rich are mostly composed of kids and teenagers, it means that software will mostly be built and used by young people. Think social media, Roblox, chat, etc, but coded by teenagers for teenagers
we're approaching a timeline where instead of going to school, getting a job, getting married, and having kids -- the linear form of life we've had for 100+ years -- we will see kids go start to building products and starting companies from a young age. This means huge disruption for universities and society, but also that we will see people build build build. A good thing IMHO.
The future will be built by young people, for young people, and billions will be made as a result
English

@IntuitMachine @AnthropicAI Based amount on the amount of fork that repo has over the past week, there seems to be a lot cooking not just with anthropic. A good and practical fully autonomous agent is a probable next checkpoint, it think we will see a lot of these
English

Will @AnthropicAI release something called "ClaudeBot"?
English

This is the one prompt that stops AI from gaslighting you.
Force AI to tell the truth.
No sugarcoating. No hallucinations. No fake confidence.
Brutally honest answers. Every time.
I packaged my reality filter prompt into a plug-and-play guide
To get it, just:
→ Comment “REALITY”
→ Follow me (so I can DM)
English

Michael Chomsky reveals he charges ~ $1,500 to setup OpenClaw and it takes him less than an HOUR
“It’s 15 minutes where I go in and we talk about all your requirements, what you want to achieve and what integrations you want”
“Then I set things up remotely and we schedule a second 30 minute meeting for me to set up integrations, permissions and also set it up in Telegram for you. By the end of that second meeting you should be chatting with your bot”
English

@shitanshu_11 Nuclear facilities targeted drawn on map
mapscroll.ai/post?queryId=o…
English

@X22Report Nuclear facilities targeted drawn on map
mapscroll.ai/post?queryId=o…
English

@The_Kyle_Mann Nuclear facilities targeted drawn on map
mapscroll.ai/post?queryId=o…
English

@IntuitMachine Also depends on how good or bad the existing codebase, a bad thousand lines function will be tricky to rewrite without breaking the original usecase
English
















