LuckyNonce

[LuckyNonce @randNonce]

@DavidBalderston @thsottiaux @OpenAIDevs same

[LuckyNonce @randNonce]

@trashpandaemoji @badlogicgames @mitsuhiko my next step is prob clone your harness

[LuckyNonce @randNonce]

@trashpandaemoji @badlogicgames @mitsuhiko I’ve sort of stumbled upon this as well. I built a custom cli to let me deploy apps, set up proper CI/CD, SSO etc… and I started to run codex thread within the cli repo to add new templates and features to the CLI as I needed them while working on other repos

[LuckyNonce @randNonce]

@OpenAI are these open source?

[LuckyNonce @randNonce]

@trashpandaemoji let us know your findings!

[LuckyNonce @randNonce]

@trashpandaemoji but will it not ended reading more than necessary with search | list | get than the frontmatters that get loaded at the start of thread currently?

[LuckyNonce @randNonce]

@jasonkneen @tinyworldsapp Love the aesthetic

[LuckyNonce @randNonce]

@SIGKITTEN @OpenAI @ajambrosino so inspiring

[LuckyNonce @randNonce]

@trashpandaemoji what dashboard is that from? It would be cool to be able to easily auth into all your different accounts to really see total clanker stats

[LuckyNonce @randNonce]

@trashpandaemoji Humm there should be a market to resale your unused tokens to the dire

[LuckyNonce @randNonce]

@trashpandaemoji 503 service unavailable

[LuckyNonce @randNonce]

@trashpandaemoji @tekbog noooo I don’t like that future. I want to believe that builders will still have an edge for awhile

[LuckyNonce @randNonce]

@deepfates @trashpandaemoji lol I’ve learned so much in the process

[LuckyNonce @randNonce]

@judahrhodie buy signal triggered on this one. glad to see confluence

[LuckyNonce @randNonce]

is there any best practice that the team has noticed?

[LuckyNonce @randNonce]

@thsottiaux is there any documentation or research that shows the performance differences of codex if you keep switching thinking modes? Or use codex x-high on task that really should be for low?

[LuckyNonce @randNonce]

@trashpandaemoji @sama I’ve been surprisingly efficient with my token usage recently. I do feel fomo that I should try to maximize more with parallel workflows but my own human context window gets cluttered

[LuckyNonce @randNonce]

@trashpandaemoji @sama need to maximize those tokens