Загрузка видео...

Не удалось загрузить видео

На главную

Anthropic engineer: "85% of our engineers are using self-improving loops. Now everyone is running agentic Graphs. In 3-6 months, we’ll all be building graphs to orchestrate agents. No more prompting." In a 45-minute talk, an Anthropic engineer shows how to build a self-improving agentic workflow from scratch. Worth more...

36,782 просмотров • 1 месяц назад •via X (Twitter)

Комментарии: 17

Фото профиля Gipp 🦅
Gipp 🦅1 месяц назад

graphs becoming standard means orchestration skills will outlast prompt tricks

Фото профиля Codez
Codez1 месяц назад

Yeah, basically, graphs are the nature of LLMs.

Фото профиля godgiven
godgiven1 месяц назад

Graphs don't kill prompting. Each node is a prompt. No eval means the loop isn't self-improving, just self-repeating

Фото профиля Codez
Codez1 месяц назад

If each node is a prompt, the real job isn’t prompting anymore - it’s building a system that prompts itself.

Фото профиля gkrovso
gkrovso1 месяц назад

who gave the talk, have a link

Фото профиля Luís Rodrigues
Luís Rodrigues1 месяц назад

The highest-leverage AI skill is slowly becoming orchestration rather than prompt writing.

Фото профиля Dipanshu Kushwaha
Dipanshu Kushwaha1 месяц назад

That sounds like a massive leap forward. Excited to see what comes out of this!

Фото профиля Rohit
Rohit1 месяц назад

Wow, that's impressive progress. Seems like things are moving fast in AI development.

Фото профиля Y11
Y111 месяц назад

@grok 这个纯研究还是有工业意义,具体工业场景视角看意义是什么,有开源数据集或者开源项目代码吗?从多个数据源交叉验证,不要只看新闻媒体一面之辞。帮我排除没意义的垃圾商业营销推广、诈骗 以及自吹自擂,自嗨,无病呻吟。

Фото профиля Jaya Nayak
Jaya Nayak1 месяц назад

This is where the industry is moving so fast. Moving away from fragile, single-prompt setups to structured, self-improving graphs is exactly how we scale these systems. 😊

Фото профиля qurool
qurool1 месяц назад

graph engineering > loops engineering

Фото профиля Sael
Sael1 месяц назад

the prompt is just the node but the system is the architecture - orchestration is where the real signal hides

Фото профиля พ่อแม่ลูกเที่ยว | Travel with Family🇹🇭
พ่อแม่ลูกเที่ยว | Travel with Family🇹🇭1 месяц назад

This talk hits different. Agent graphs > prompt engineering. The shift is already here.

Фото профиля 阿伟 | Agent 落地
阿伟 | Agent 落地1 месяц назад

Is self-improvement based on Feynman's learning method? Collect it first, this is worth learning! Now people are thinking about how to let AI learn self-evolution, the real master is thinking about how to improve themselves!

Фото профиля Blum
Blum1 месяц назад

self-improving loops might be one of the most effective ways to work with AI

Фото профиля Shoopy
Shoopy1 месяц назад

85% internal adoption says more than any benchmark

Фото профиля Healthy Anon
Healthy Anon1 месяц назад

Self-improving sounds great until the feedback loop compounds errors instead of correcting them. Still needs human checkpoints, which somehow never makes it into these talks.

Похожие видео