It's interesting how much this makes you want to write Unix-style tools that do one thing and only one thing really well. Not just because it makes coding an agent simpler, but because it's much more secure!
You should write an agent
11–20 of 409 posts
Re: You should write an agent
#12Write an agent, it's easy! You will learn so much!
... let's see ...
client = OpenAI()
Um right. That's like saying you should implement a web server, you will learn so much, and then you go and import http (in golang). Yeah well, sure, but that brings you like 98% of the way there, doesn't it? What am I missing?
Re: You should write an agent
#13It's interesting how much this makes you want to write Unix-style tools that do one thing and only one thing really well. Not just because it makes coding an agent simpler, but because it's much more secure!
You could even imagine a world in which we create an entire suite of deterministic, limited-purpose tools and then expose it directly to humans!
Re: You should write an agent
#14Write an agent, it's easy! You will learn so much! ... let's see ... client = OpenAI() Um right. That's like saying you should implement a web server, you will learn so much, and then you go and import http (in golang). Yeah well, sure, but that brings you like 98% of the way there, doesn't it? What am I missing?
That OpenAI() is a wrapper around a POST to a single HTTP endpoint:
POST https://api.openai.com/v1/responsesRe: You should write an agent
#15Maybe we should write an agent that writes an agent that writes an agent...
Re: You should write an agent
#16Write an agent, it's easy! You will learn so much! ... let's see ... client = OpenAI() Um right. That's like saying you should implement a web server, you will learn so much, and then you go and import http (in golang). Yeah well, sure, but that brings you like 98% of the way there, doesn't it? What am I missing?
That's not an agent, it's an LLM. An agent is an LLM that takes real-world actions
Re: You should write an agent
#17There's something(s) about @tptacek's writing style that has always made me want to root for fly.io.
Re: You should write an agent
#18Write an agent, it's easy! You will learn so much! ... let's see ... client = OpenAI() Um right. That's like saying you should implement a web server, you will learn so much, and then you go and import http (in golang). Yeah well, sure, but that brings you like 98% of the way there, doesn't it? What am I missing?
I think you might be conflating an agent with an LLM.
The term "agent" isn't really defined, but its generally a wrapper around an LLM designed to do some task better than the LLM would on its own.
Think Claude vs Claude Code. The latter wraps the former, but with extra prompts and tooling specific to software engineering.
Re: You should write an agent
#19Write an agent, it's easy! You will learn so much! ... let's see ... client = OpenAI() Um right. That's like saying you should implement a web server, you will learn so much, and then you go and import http (in golang). Yeah well, sure, but that brings you like 98% of the way there, doesn't it? What am I missing?
maybe more like “let’s write a web server but let’s use a library for the low level networking stack”. That can still teach you a lot.
Re: You should write an agent
#20Write an agent, it's easy! You will learn so much! ... let's see ... client = OpenAI() Um right. That's like saying you should implement a web server, you will learn so much, and then you go and import http (in golang). Yeah well, sure, but that brings you like 98% of the way there, doesn't it? What am I missing?
An agent is more like a web service in your metaphor. Yes, building a web server is instructive, but almost nobody has a reason to do it instead of using an out of the box implementation once it’s time to build a production web service.