Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Agents API

developers.openai.com

Post reply on HN
Print view View original

71–80 of 202 posts

Re: OpenAI Agents API

#71

Post by sejje »

krashidov wrote: post #48
windexh8er wrote: post #37

Earlier quoted context omitted.

Considering the harness needs to be running how else would this work? Pretty easy these days with old school tools like tmux but more modern tooling like herdr [0] is really the path you'd want to take. [0] https://herdr.dev/

> Considering the harness needs to be running how else would this work? you can just make new sessions for each new task?

i tend to do this, or at least every so often.

i just give it a config (agents.md etc) to where it knows what's going on, or can figure it out

Re: OpenAI Agents API

#72

Post by wiei »

bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

Agents are the wrong paradigm entirely and have limited places where they actually belong.

Going off and searching the web isn't really it.

You need to create 'new worlds' where they can operate best - and even then constrain what it does.

Re: OpenAI Agents API

#73

Post by sejje »

wyre wrote: post #30
kingstnap wrote: post #20

This is pretty interesting in a lot of non-surface-level ways. I can see OpenAI pushing for this as a sort of more durable moat compared to the now huge number of agentic harnesses that run on your own machine. This might be getting the foot into some sort of bundling as well. Like unrestricted models or custom fine tuned agents inside this and not providing direct APIs to those endpoints. That being said I don't see…

>GPT Work runs on your own machines...is sort of the whole point. Which is also why they want to remove it from your machine. Call it conspiratorial, but I keep thinking about "You'll own nothing and be happy." It seems like the industry is quickly moving in a direction where devices are turning into gateway into the cloud, and personal computing will turn into a hobby that prices out the average individual.

I mean, they didn't say "you can't download the product of your work" or something.

Re: OpenAI Agents API

#76

Post by skinfaxi »

bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

I think things like onecli are the direction we will take. The secrets and state will be proxied api calls.

Re: OpenAI Agents API

#77

Post by messh »

bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

[dead]

Re: OpenAI Agents API

#78

Post by surgical_fire »

bob1029 wrote: post #65
bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

> building your own harness is a huge undertaking, a deep rabbit hole. I eventually gave up on this task. It's not possible to fight OpenAI or Anthropic's engineering teams. Their reasoning models have all kinds of undocumented back door access to the base models that you'd never be able to replicate from the outside. Even if you had full access you would not have the engineering man hours or experience to keep up. I…

> It's not possible to fight OpenAI or Anthropic's engineering teams

And yet, I find Pi so much better to work with than Claude Code.

Re: OpenAI Agents API

#79

Post by bmurphy1976 »

andrewchambers wrote: post #31

I've recently had great success running codex in a regular qemu VM and using codex remote control to talk to it from my phone. Honestly works extremely well as a personal assistant. I can see why turning it into an API makes sense, just be aware you might not need to lock yourself in if you can setup your own VMs.

I've been running Hermes inside a remote docker container connected to Slack bound to a Codex account. It's actually pretty great, I prefer this approach for a lot of things. Because it's in a Docker container I have 100% control over the configuration. It may do some crazy stuff, but I know it's not going to start exfiltrating my AWS SSO tokens or SSH keys from my laptop.

Re: OpenAI Agents API

#80

Post by lhk931122 »

Six months into customizing my own Claude Code harness, I've settled on assuming Anthropic and OpenAI will just handle all of it, except turning my own flows into skills.
Post reply on HN