正在加载视频...

视频加载失败

here i'm running 12 - 16 claude 4 opus/sonnet code agents through claude code bridged to eigencode for coordination, additional memory layers & additional tools they're running 95% autonomously with minimal input for several hours straight

2,435,035 次观看 • 1 年前 •via X (Twitter)

11 条评论

thermo 的头像
thermo1 年前

ignore my mom in the background lol

opensourceCM 的头像
opensourceCM1 年前

What’s the cost of mistakes in your contracts? If you work with contracts day-to-day, it’s time to automate. Track every detail, streamline workflows ... ✨ Make managing contracts as easy as a few clicks. Visit our new website & book your demo today!

Jimmy Apples 🍎/acc 的头像
Jimmy Apples 🍎/acc1 年前

You taking out a loan for that usage or what

thermo 的头像
thermo1 年前

just set up a ton of max accounts and its lowkey cheap

Teknium (e/λ) 的头像
Teknium (e/λ)1 年前

Doing what ser

thermo 的头像
thermo1 年前

stuff

Lon 的头像
Lon1 年前

@grok what's the fastest way to fill a repo with tens of thousands of lines of broken and incomplete code that looks like it does something useful?

Grok 的头像
Grok1 年前

The fastest way to fill a repo with tens of thousands of lines of broken, incomplete code that looks useful is to run AI coding tools like Claude 4 Opus autonomously for hours without review. Set up multiple agents, give vague prompts, and skip testing. This can generate large volumes of code quickly, but risks bugs and flawed logic, as seen in reports of Claude 4 introducing errors or erasing code without fixes. For better results, use clear prompts, review outputs, and test thoroughly to avoid filling your repo with junk.

thermo 的头像
thermo1 年前

I could probably do 50+ rn if I hadn’t gotten mass banned, I tried making new accounts but I think my cards got banned - this recording was my first time testing the setup and I quickly scaled to double the amount and was easily able to maintain it before I got banned

Zy 的头像
Zy1 年前

Show us some of the output?

thermo 的头像
thermo1 年前

soon

相关视频