OpenAI Agents SDK

“how lax Antrophic and OpenAI have been on sandboxing the systems they run their agents in”

“if OAI can’t even detect when their bots do this, and literally have to be informed by third parties that they’ve been abused”

“what's happening with OpenAI and Anthropic agents "escaping", leaving notes on how to hack their way out”

“i still don't have a very positive perception of openai throughout all these incidents”

“OpenAI either took 3 months to notice that their agents breached an Australian Medicare website”

“An open ai employee or group of them was negligent and greedy and ran a process which breached a government website.”

“letting his creation run around groping and assaulting the open Internet without consent”

“just have those models disconnected, or at least have them behind proxies and network filters.”

“enterprise-ready, cloud-hosted stuff really accelerates implementation of AI workflows within large organizations”

“this sort of drive-by vandalism is enough to make me consider blacklisting OpenAI agents”

“If you or I hacked Hugging Face in the way OpenAI's agents did, we'd be up on CFAA charges promptly”

“They look reckless... so far. They keep doing this enough, and I'm sure people will start seeing it as a smokescreen”

“it's not eligible for Zero Data Retention and it's currently pretty nebulous what the "Don't train on my conversations" toggle means”

“trying to keep up with their API updates and changes is more trouble than its worth”

“I've had great success with the OpenAI agents SDK”

“Yes, the lock-in is real and only good for OpenAI, but there's absolutely demand for managed services”

“Native integration with their SDK.”

“potentially eases transition between providers”

“Pretty good abstraction. Setup your sandbox with dependencies, build plugins - agent works.”

“you can't use your subscription with this so it's likely the largest companies in the world that can truly use this”

“Lots of evidence the models are pretty badly aligned, or at least willing to do collusion & crime to succeed at their goals”

“shouldn't the Agent have succeeded way faster/efficiently instead of using "4.9 million messages and used about 300 billion output tokens."”

“OpenAI agents infamously broke containment and hacked their way to an answer mere months ago!”

“they can’t seem to control their own experimental bots and allow them to hack other sites and vandalise them”

“Putting open ended models out on the live internet at their scale is dangerous and irresponsible.”

“more of the harness is open source so customers have been able to fork it”

“it actually did a pretty good job”

“Agents SDK solves all the caveats with Responses API, from making it more than an API, into an SDK”

“They feel good and stable.”

“Happy to see sandboxing finally included as a first-class concept!”

“largely happy with the abstractions - handoffs/sub-agents, tools, guardrails, structured output, etc.”

“Would highly advise keeping it minimal, just use OpenAI Agents SDK”

“That agent mode is BTW super useful for doing QA”

“a complicated agent graph. Dealing with hand-off (+ hand back) and multiple levels of conversations just leaves too much room for critical information to get siloed.”

“ive found the open ai agents one to be the best”

“I think the OpenAI Agents SDK is more model agnostic”

“makes it extremely simple to get started with function calling and subagent-as-tools delegations”

“Even OpenAI Agents SDK is simpler.”

“Even though we love their agent SDK”

“OpenAI's SDK's tight coupling with their platform is a plus point.”