Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 1 Monat •via X (Twitter)

17 Kommentare

Profilbild von Gipp 🦅
Gipp 🦅vor 1 Monat

graphs becoming standard means orchestration skills will outlast prompt tricks

Profilbild von Codez
Codezvor 1 Monat

Yeah, basically, graphs are the nature of LLMs.

Profilbild von godgiven
godgivenvor 1 Monat

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

Profilbild von Codez
Codezvor 1 Monat

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

Profilbild von gkrovso
gkrovsovor 1 Monat

who gave the talk, have a link

Profilbild von Luís Rodrigues
Luís Rodriguesvor 1 Monat

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

Profilbild von Dipanshu Kushwaha
Dipanshu Kushwahavor 1 Monat

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

Profilbild von Rohit
Rohitvor 1 Monat

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

Profilbild von Y11
Y11vor 1 Monat

@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。

Profilbild von Jaya Nayak
Jaya Nayakvor 1 Monat

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. 😊

Profilbild von qurool
quroolvor 1 Monat

graph engineering > loops engineering

Profilbild von Sael
Saelvor 1 Monat

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

Profilbild von พ่อแม่ลูกเที่ยว | Travel with Family🇹🇭
พ่อแม่ลูกเที่ยว | Travel with Family🇹🇭vor 1 Monat

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

Profilbild von 阿伟 | Agent 落地
阿伟 | Agent 落地vor 1 Monat

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!

Profilbild von Blum
Blumvor 1 Monat

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

Profilbild von Shoopy
Shoopyvor 1 Monat

85% internal adoption says more than any benchmark

Profilbild von Healthy Anon
Healthy Anonvor 1 Monat

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.

Ähnliche Videos