zekone

thank you sir i will fix this

or something will fix this

https://github.com/aavetis/ai-pr-watcher/issues/21

thanks for posting my project bradda

Codex UX is wonky. if it makes changes for you and you create a PR with it; then have follow interactions to further modify, it will result in a new PR for every subsequent change. it doesn't update or modify an existing PR.

Copilot does. which is maybe why its numbers are lower; but I prefer this interaction more

hi folks, would appreciate your thoughts and feedback on this kind of user experience. while ai models are increasingly becoming multi-modal, our experiences are still synchronous and via single mode.

here i offer a demo of what a combined interaction would look like with speech-to-speech and a visual canvas, mimicking how people normally give presentations or convey complex ideas.

thanks

https://twitter.com/albfresco/status/1728435103443845508

why is Azure a no-go? - it's the only other place to get an OpenAI service - you can have dedicated capacity for it if you're big enough and it's worth it - you can literally turn off public endpoint for it and make it inaccessible, and expose only through a proxy like this - you can load balance across multiple openai deployments for regional efficiency and rate limit issues

(not trying to push for Azure in general, just trying to understand why even in the OpenAI use case, Azure is a no-go)

LLM Observability tools have taken off, but they all result in you sending away your generations and chat history. That is, if you actually have users.

If you want to keep that all for yourself, I made a small script that deploys a simple monitoring solution that you control in your own resource group on Azure.

Feedback / critiques / suggestions all welcome, thanks.

https://github.com/aavetis/azure-openai-logger

onboarded and started using it in literally 2 minutes. nice