[flagged]
OpenAI Agents API
181–190 of 202 posts
Re: OpenAI Agents API
#182[dead]
Re: OpenAI Agents API
#183[dead]
Re: OpenAI Agents API
#184I 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…
> they’re stuck using their own proprietary frontier models and those aren’t actually the best choice for most agents right now
Are they stuck? What's preventing them from using open models or creating models more suited for those tasks?
Re: OpenAI Agents API
#185Buried in there, note you can opt to self-host your sandbox https://developers.openai.com/api/docs/guides/agents-api/env... That makes this much more enticing, and potentially eases transition between providers.
Then why tf do i need their api
Can potentially have private networking advantages, e.g. internal api's.
Re: OpenAI Agents API
#186Earlier quoted context omitted.
Correct me if I'm wrong, but the harness will always be dependent on the underlying model, and useless without it. All custom harnesses are being built, could be obsolete in the next big-generation-jump of the models. I might be absolutely wrong, but "harnesses" / cc-derivatives became "good enough" only maybe a year ago max. Before that, people were pushing for gigantic folder structures with custom documents and "p…
Doesn't apply to every scenario where agents are useful. Think about businesses - most business processes are not optimized this way. They are mostly a conglomeration of hierarchy, relationships, customs, IP, etc. Model development will never cross such paths. Thus, harnesses are needed. A foundational system that covers 80% of business processes has value, and I'm targeting that problem --- https://github.com/rush86…
Counter point to “complex businesses” is they’re currently buying Copilot licenses for their employees, with the hopes it can intermingle with Office365. Very ineffective, I think, buy from my exposure the “non-tech” side of things is not on the same timeline as us.
That’s also one of the reasons why I think harnesses might be obsolete in a year, or re-defined completely.
Obviously, once again, I might be completely wrong. But my thesis is investing hard on any model/harness/custom builds might be counter productive given the speed of development. It’s not easy, but having a nimble org where you can swap things around might be a good call.
Re: OpenAI Agents API
#187Earlier quoted context omitted.
I don't think anyone who's tried something else can like claude code. The only reason to use it is the subsidized plan and nothing else.
But it does have some very cool features built in I haven't seen rolled in elsewhere. Sessions can talk to one another out of the box. Two left arrows and you see all the sessions. Automatic remote control to pick up a session from another computer or even on your phone. So convenient! I could patch this together with Herdr and OMP and some custom server stuff but it works right out of the box!?
Cursor does all that and actually lets you look at the code
Re: OpenAI Agents API
#188I 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…
What is your use case? Your business model?
There is no "one harness". I don't feel your pain. I know, what quality has to be ensured, what's within boundaries and what not etc.
I work for price sensitive industries and here some information has to be factual correct. The error rate is 0% so far, 100% accuracy.
So what are you trying to harness?
Re: OpenAI Agents API
#189I 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…
> A competitor who is not an LLM lab gets their pick of the market at any given moment
Exactly this. We're building an Agents-as-a-service API, would love to get your feedback: https://www.ellipsis.dev/docs/sessions
Re: OpenAI Agents API
#190Earlier quoted context omitted.
do you mean like a cloud agent provider? What we're working on at noriagentic.com may be relevant -- you can fire events from slack/web/cli to kick off an agent in a box and talk to it as if it was running local
Do you guys support projects that span multiple repositories? (and can create multiple PRs across them?)
yea of course. tldr: we set up a vm that the agent can run in, anything you can do on your computer you can ~do in the system.
feel free to dm me, amol at noriagentic dot com