OpenAI Symphony
github.comThe sample code is written in Elixir, however, they also release the full specs using which one can generate the application in the language of one's choice. I'm curious if this is really so straightforward.
Similar to the pattern for making StrongDM's attractor autonomous agent: https://www.strongdm.com/blog/the-strongdm-software-factory-...
https://github.com/strongdm/attractor
with a max plan and a week, you too can have one of these by typing: Ok, keep going. into the terminal 49 times.
It's been a month since they unveiled The Attractor and already there are hundreds of open source implementations:
https://factory.strongdm.ai/products/attractor#community
https://github.com/search?q=strongdm+attractor&type=reposito...
I have a fork, it's excellent. Complementary to something like symphony which doesn't deliver the harness you need to make working software, attractor's graph orchestration inside the loop that symphony creates can set determinative workflows with the harness openAI (and StrongDM) were talking about using to test. My personal system uses property testing, fault injection and fuzzing layered on top of playwright and e2e testing behaviors against a digital twin system I have to credit StrongDM for inspiring again.
They trained on this song: "Just like the Pied Piper Led rats through the streets We dance like marionettes Swaying to the symphony of destruction"
The specs are inscrutable agent slop. I want it to tell me what it does and instead it just lists database fields. It mentions a state machine and then proceeds to not describe the state machine.
If I wasn’t so attuned to agent slop, I’d be thinking I’m just too dumb to get it but no, whatever GPT model wrote this is not good enough (and the fact this was published by OpenAI suggests this is not an operator skill issue).