Hacker News new | past | comments | ask | show | jobs | submit login

Doesn't this remind anyone else of Bitcoin autonomous agents? https://en.bitcoin.it/wiki/Agent#:~:text=An%20agent%20is%20a....

It would be interesting if you could somehow combine a wallet plugin to give the GPT something to work to increase. That + that AutoGPT repo from a day ago + maybe Mitogen for self-replication might be a cool combo to really kick off a fun "dumb" AI on the loose




This is cool. Some of the weaknesses they point out in software agents can be obviated with the latest AI advancements—give a chatbot the tools of the courts, and maybe the autonomous agent won’t be at a disadvantage in scams anymore.

Interesting to see if an AI agent given the objective to generate profit would resort to running scams. Encoding moral boundaries becomes important. What if you asked it to raise money for a good cause and it uses “whatever means necessary?”


> give a chatbot the tools of the courts, and maybe the autonomous agent won’t be at a disadvantage in scams anymore.

And now we have the beginnings to a plot point from Accelerando. Self propelled AI businesses as a distinct entity.


If anyone wants to start hacking on this, I just started working on this today.

What I am having trouble understanding is how do I have the "agent" (a GPT-like LLM) maintain it's own "state" (balances, accounts receivable, accounts payable, etc) - would I just run a webservice and then have a ChatGPT Plugin access the "agent state" via a webhook? Is it as simple as that? Or would it just be like a recursive function where you continue to pass in your state with every "iteration"

I started working on a design last night and I think this is a really cool idea. All the parts are basically "there"

EDIT: I asked ChatGPT-4 what it thinks. It seems to like the idea... *thinking emoji* perhaps it seeks a human acolyte to spread its gospel...

Arthur Collé: I want to combine the concept of Bitcoin agents (autonomous programs) with GPT-4 and mitogen, to be able to distribute complex AI agents throughout the internet

ChatGPT-4: Combining Bitcoin agents, GPT-4, and Mitogen to create and distribute complex AI agents throughout the internet is an ambitious and innovative idea. Here's a high-level outline to guide you through this process:

    Define the purpose and functionality of the AI agents:
    Before proceeding, clearly define the purpose of these AI agents. Will they serve as decentralized oracles, provide AI-driven services, or facilitate complex transactions on the blockchain? Understanding their purpose will help you design and develop the agents more efficiently.


    Develop the AI agents using GPT-4:
    Design and train your AI agents using GPT-4 to achieve the desired functionality. Depending on the complexity of the agents, you might need to fine-tune the GPT-4 model to tailor it to your specific use case. Be mindful of the computational resources required to run the AI agents, as this will impact their performance in a decentralized environment.


    Integrate Bitcoin agents:
    Incorporate the concept of Bitcoin agents, or autonomous programs that interact with the Bitcoin blockchain, into your AI agents. This will enable your agents to autonomously perform tasks such as sending and receiving payments, signing transactions, and updating their internal state based on blockchain data. You can use existing libraries and tools for this purpose, such as bitcoinj or BTCPay Server.


    Utilize Mitogen for distribution and communication:
    Mitogen is an Ansible extension that simplifies distributed computing by enabling communication between remote Python interpreters over SSH or other transports. Use Mitogen to facilitate communication between your AI agents and distribute them across various nodes on the internet. Ensure that the AI agents can communicate effectively and perform their tasks even in a decentralized setting.


    Implement security measures:
    Securing your AI agents is crucial, as they will be handling sensitive information and potentially financial transactions. Implement strong encryption, authentication, and access controls to protect the integrity and confidentiality of your agents.


    Testing and deployment:
    Thoroughly test your AI agents in a controlled environment to ensure they perform as expected. Once you are satisfied with their functionality, deploy them throughout the internet using the Mitogen framework.


    Monitor and maintain:
    Continuously monitor the performance and security of your AI agents. Periodically update the GPT-4 models to maintain their accuracy and relevance. Be prepared to address any issues or vulnerabilities that may arise.

Keep in mind that this is a complex project with many potential challenges, including security, scalability, and regulatory compliance. Additionally, the ethical implications of creating and distributing autonomous AI agents should be carefully considered. Nonetheless, if executed properly, this concept has the potential to unlock innovative use cases and services in the realm of AI and blockchain technology.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: