Загрузка видео...

Не удалось загрузить видео

На главную

SpaceXAI engineer (ex-Cursor): "99% of people still use GrokBot like Google and only 1% are building teams of self-learning agents i'm running 10-20 Grok cloud agents in a loop. I have a Chief of Staff, a PM agent and 15+ worker agents" in a 20-minute workshop, a SpaceXAI engineer...

2,323,948 просмотров • 3 дней назад •via X (Twitter)

Комментарии: 20

Фото профиля leopardracer
leopardracer3 дней назад

saved this! worth watching

Фото профиля Codez
Codez3 дней назад

Yeah bro. When SpaceXAI engineers are talking I’m listening

Фото профиля helicerat
helicerat3 дней назад

useful for anyone stuck at two or three agents

Фото профиля joey gallagher
joey gallagher3 дней назад

Like what are normal people doing during the day that I must be missing. I’m an electrician. That deals with the rich of rich to the dirt poor. What am I missing cause everything I see on AI is not for normal people usage.

Фото профиля Sandip Patil
Sandip Patil2 дней назад

Ask it to create and read. Don't let it modify and delete. In the excitement it deletes thing without consent. Be careful

Фото профиля Finch⚡️
Finch⚡️2 дней назад

Isn’t the same thing that people were doing with Claude Code at the beginning of summer?

Фото профиля Marko
Marko2 дней назад

The jump from "1 agent" to "15 workers + a Chief of Staff" only holds up if the Chief is actually enforcing scope - otherwise you've just built one agent with 15 more places for a wrong assumption to hide

Фото профиля Smith_X
Smith_X3 дней назад

Ngl, I'm still part of the 99% using it as a glorified Google lol.

Фото профиля aven wong
aven wong3 дней назад

@grok 可以帮我把视频里的教学内容形成文字教程发给我吗,记得用傻瓜式的,我是小白

Фото профиля karcharodon
karcharodon2 дней назад

People should need to learn

Фото профиля V1nT
V1nT2 дней назад

Everyone should need to learn

Фото профиля Adel Bucetta
Adel Bucetta3 дней назад

that's not surprising most people still don't grasp the scale difference between querying an existing model and building custom self-learning agents from scratch

Фото профиля Sridhar A
Sridhar A2 дней назад

the interesting shift isn't more agents, it's agents becoming an org chart. once the coordination layer works reliably, a small team can operate very differently.

Фото профиля Pitchfork & Torch ♞
Pitchfork & Torch ♞2 дней назад

@SpaceXscoop Because we run out of usage lol

Фото профиля Money Bunny
Money Bunny3 дней назад

Running multiple agents in parallel is genuinely changing how solo builders operate now.

Фото профиля Vic H
Vic H2 дней назад

@grok find direct youtube link

Фото профиля unidentified
unidentified2 дней назад

amazing video @Kr1yo1

Фото профиля Stan | AIwithStan
Stan | AIwithStan2 дней назад

Yeah, but how do you do that without using a weeks worth of undisclosed tokens in half a day?

Фото профиля Emma Rodriguez
Emma Rodriguez2 дней назад

"99% still use it like Google" is brutal but honestly accurate

Фото профиля Jordan Lee
Jordan Lee2 дней назад

10-20 agents in a loop is the same number everyone lands on

Похожие видео