Nico Arkhipenko (@narkhip) header
Nico Arkhipenko (@narkhip) profile picture

Field CTO and Grok Bot team @SpaceXSI 🇦🇷 in SF

San Francisco, CA
Joined April 2009
Since joining Cursor I’ve been living on Grok Bot. Nothing has hit me like this since we first started chatting with LLMs. I’ve stopped opening most apps. The best UI is messaging teammates. You create Bots just by chatting with them. They learn from your feedback, they coordinate, and what used to take a pile of prompts is now one ask. The work actually moves. I’ve seen others try to solve this, and I was always disappointed. What’s different about Grok Bot is the first principles design: dead simple on the surface, serious cloud infrastructure underneath. That's what finally makes the promise of a personal AI assistant real. Once you try it, you’ll never go back.
Introducing Grok Bot, now in early beta. Bots are AI teammates that do real work for you. They sign in to your tools, use them just like you do, and come back with finished work.
34
12
1
413
25,595
Coding can't be solved while bugs exist. Every bug is a counterexample: code that doesn't do what you meant, and doing what you meant is the job. Agents solved code generation. The gap between intent and behavior is wide open, and closing it is what @poteto means by engineering. The code grows on its own now. The scaffolding is the job.
if your definition of coding is just the act of typing code, then yes, it's solved. agents can type code faster than anyone can. but i think most of us think of coding as the act of solving problems with code. in that definition, coding is definitely not solved. agents can generate code quickly and build whatever you want, but without the right constraints, they end up causing more problems than they solve. i think of this like my gardening analogy. agents are like magic beans that grow in any condition, but in wild and unpredictable ways. if you put the right scaffolding around them however, they can grow into whatever shape you want. you still want humans thoughtfully and intentionally steering this outcome. we have a name for them: engineers. agents have greatly lowered the barrier to entry to doing engineering. what was once the domain of those who understood syntax and logic is now accessible to anyone who can explain their ideas. english is a new programming language for engineering outcomes with agents. now, even ordinary people can build impressive software. and the good ones will learn engineering through first principles. as someone who is a self-taught programmer (i first learned how to code through Excel macros!), this is incredibly exciting to me, and i can't wait to see what everyone learns and builds in this new world. let a thousand gardens bloom!
2
9
1,796