@EchoShao8899: Coding agents are general agents, and every company is evolving models and agent harnesses—but how to make them benefit…

X AI KOLs Following News

Summary

This podcast episode features Zora Wang from CMU discussing the future of AI agents, focusing on skills, memory, and collaboration to make them benefit a broader audience beyond the tech bubble.

Coding agents are general agents, and every company is evolving models and agent harnesses—but how to make them benefit more people, rather than just a small tech bubble? In EP6 of @augmind_fm, we sat down with Zora Wang (@ZhiruoW) from CMU to talk about Skills, Memory, Collaboration, and What’s Next for AI Agents. Zora started her research in program synthesis and has since done impactful work on coding models and agent workflow memory. I still remember a long conversation we had last year about where agents were heading, after which I somehow convinced her to work more on human-agent collaboration—and we’ve been collaborating closely ever since :) It’s an amazing opportunity to reflect on many things that happened in the past year, and hear Zora’s perspective on what comes next for AI agents.
Original Article
View Cached Full Text

Cached at: 08/16/26, 08:11 PM

Coding agents are general agents, and every company is evolving models and agent harnesses—but how to make them benefit more people, rather than just a small tech bubble?

In EP6 of @augmind_fm, we sat down with Zora Wang (@ZhiruoW) from CMU to talk about Skills, Memory, Collaboration, and What’s Next for AI Agents. Zora started her research in program synthesis and has since done impactful work on coding models and agent workflow memory. I still remember a long conversation we had last year about where agents were heading, after which I somehow convinced her to work more on human-agent collaboration—and we’ve been collaborating closely ever since :)

It’s an amazing opportunity to reflect on many things that happened in the past year, and hear Zora’s perspective on what comes next for AI agents.

Augmented Mind Podcast (@augmind_fm): “If you look at … where the economic value concentrates, the software engineer only captures around less than 5% of human employment, but there are a lot of other occupations out there that are using computers.”

For EP6, we welcome @ZhiruoW, a CS PhD student at Carnegie Mellon

Similar Articles

@0xCodez: https://x.com/0xCodez/status/2089393338977829278

X AI KOLs Timeline

This article outlines a 12-step roadmap for AI Agent Engineers in 2026, focusing on seven interconnected pillars like context, tools, and memory, with Claude-based workflows to build reliable production agents.

@SuJinyan6: https://x.com/SuJinyan6/status/2073955240349770069

X AI KOLs Timeline

This blog post by SuJinyan6 examines the evolution of AI agents from simple LLM+tool use to context engineering and long-running harnesses, citing Anthropic's recent work and discussing how agent capability is now a system-level property involving multiple components.