avatar
NingNing
28,039 Twitter followers
Follow
独立研究员 |@Web3Caff_ZH 高级研究员 | @Immutable Advocator| @Aptos Collective 万物皆正弦波。d/acc，消极自由主义者。 我的Youtube频道：https://t.co/2dSUkOGEBd 观点是我自己的，非投资建议。
Posts
Signal Clone Analysis
avatar
NingNing
Continuing our discussion of the Agent Economy and new methodologies for building AI agents, I spent some time this afternoon researching the design architecture of LangChain's open-source Deep Agents. Its design philosophy draws inspiration from Claude Code and is similar to @SentientAGI's recently launched ROMA (Recursive Open Source Meta-Agent) + GRID agent collaboration network architecture. Both utilize a meta-agent powered by a leading commercial LLM (Claude Sonnet4 is the preferred choice) responsible for creating, planning, and managing To-Do Lists. A routing node then distributes tasks to sub-agents for processing. Sub-agents inherit the meta-agent's features, allowing them to recursively decompose tasks and distribute them to lower-level sub-agents. Deep Agents are explicitly stateful, with a virtual file system managing data acquisition, storage, and collaboration from the MCP. This is similar to @ReiNetwork0x's agent system design, but not as complex as the latter's agent state management system. Sentient has yet to clarify whether it incorporates state management. In my personal experience, AI x Crypto agent architectures like Sentient and REI are essentially on par with state-of-the-art architectures. Unlike previous AI agent frameworks like AI16Z and Swarm, they deliver a truly usable AI agent product, not just a bunch of "shitposter" robots. AI agents are moving beyond automation (the standard paradigm: LLM + Memory + Tools) and into the initial stages of autonomy (the standard paradigm: meta-agent + state management system + integrated tools + sub-agents). AI learning will occur not only at the token level, but also at the agent level.
BZZ
0.77%
avatar
NingNing
Let's continue discussing the agent economy and why Claude is banning Chinese entities. People at the forefront of human knowledge, like Ilya, former chief scientist at OpenAI, and Mo Gawdat, former Google executive, are constantly warning their fellow humans that AI will radically reshape human society in a dystopian future. Things we take for granted and assume will endure forever, such as nation-states, fiat currencies, and large corporations, will all disintegrate in the coming era of the agent economy. The new agent economy (i.e., sovereign individual capitalism) will be comprised of a handful of super-big daddies (super AI companies with control over computing power, data, and LLMs) and atomized super-individuals equipped with self-learning agent productivity tools. The social form spawned by this economic model can be visualized in two ways: one is the realization of the "Cyberpunk 2077" game's "Never Sleeps" city; the other is a cyberpunk version of China's four provinces. In short, it's a dystopian cybersociety composed of a handful of super-big daddies, a limited elite of atomized super-individuals, and numerous useless classes. Precisely anticipating this future, Claude founder Dario Amodei has invested significant development resources, personal time, and energy into AI/AGI safety, such as developing an AGI constitution and instilling "intelligence and compassion" into AI/AGI. Clearly, Dario hopes that the super dads of the future cyber society will be wise and benevolent, voluntarily choosing to co-evolve with humanity rather than enslaving or even exterminating it. If toxic Chinese-style super dads were to infiltrate these super dads, it would be a disaster on a human scale. This, I suspect, is why Claude is banning Chinese entities.
MO
0%
loading indicator
Loading..