Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 1 ay önce •via X (Twitter)

17 Yorum

Gipp 🦅 profil fotoğrafı
Gipp 🦅1 ay önce

graphs becoming standard means orchestration skills will outlast prompt tricks

Codez profil fotoğrafı
Codez1 ay önce

Yeah, basically, graphs are the nature of LLMs.

godgiven profil fotoğrafı
godgiven1 ay önce

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

Codez profil fotoğrafı
Codez1 ay önce

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

gkrovso profil fotoğrafı
gkrovso1 ay önce

who gave the talk, have a link

Luís Rodrigues profil fotoğrafı
Luís Rodrigues1 ay önce

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

Dipanshu Kushwaha profil fotoğrafı
Dipanshu Kushwaha1 ay önce

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

Rohit profil fotoğrafı
Rohit1 ay önce

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

Y11 profil fotoğrafı
Y111 ay önce

@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。

Jaya Nayak profil fotoğrafı
Jaya Nayak1 ay önce

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. 😊

qurool profil fotoğrafı
qurool1 ay önce

graph engineering > loops engineering

Sael profil fotoğrafı
Sael1 ay önce

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

พ่อแม่ลูกเที่ยว | Travel with Family🇹🇭 profil fotoğrafı
พ่อแม่ลูกเที่ยว | Travel with Family🇹🇭1 ay önce

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

阿伟 | Agent 落地 profil fotoğrafı
阿伟 | Agent 落地1 ay önce

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!

Blum profil fotoğrafı
Blum1 ay önce

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

Shoopy profil fotoğrafı
Shoopy1 ay önce

85% internal adoption says more than any benchmark

Healthy Anon profil fotoğrafı
Healthy Anon1 ay önce

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.

Benzer Videolar