athyuttamre

Ah yes — the camera icon is to take a photo, not to show the model video in real-time. Try taking the photo and uploading it! If you're having trouble, please share a screenshot and the build number (Settings > About) with me via email at [email protected].

(Atty from OpenAI here)

>This is a move in the right direction, but there is lots of engineering still to be done!

Could not agree more. We see this as the first version of a new generation; expect many improvements in the future.

A lot of this is steerable! Our current personality is optimized for brainstorming and conversations, but you can provide custom instructions to ask it to go deep and give you info-dense or more technical answers.

Have you tried some of our deeper voices like Spruce? Would love to hear what your ideal voice is.

We're adding support to the API soon, which will let you integrate with any agent in the background. Would love to see the community go wild with it. You can sign up to be notified here: https://openai.com/form/gpt-live-1-in-the-api/

Image input is supported, but video is not today. We're working hard to bring it to you soon.

There are many delegation models possible:

1. The voice model delegates to one agent.

2. The voice model delegates to multiple agents, and keeps track of tasks.

3. The voice model delegates to an orchestrator agent, which then delegates to sub-agents and keeps track of tasks.

YMMV depending on the exact product experience you care about, because there is a tradeoff between latency and layers of delegation.

Our current implementation is backed by one model, but you can imagine this getting much better with time.

In ChatGPT, Voice doesn't yet support connectors, but we're hoping to add support soon! Once GPT-Live launches in the API, you can also build custom integrations yourself.

(Atty from OpenAI here)

Coming soon! Sign up to be notified here: https://openai.com/form/gpt-live-1-in-the-api/

(Atty from OpenAI here)

You can choose among 9 voices in the app, all newly refreshed for GPT-Live. If you meant whether it can detect multiple people, it can (like in the livestream), but not always perfect. Would love to hear your feedback once you try it.

(Atty from OpenAI here)

GPT-Live does not support video at this point, but we're working hard to introduce it soon. In the meantime, our previous Advanced Voice Mode will continue to be available and supports video.

(Atty from OpenAI here)

We're beginning the rollout now, and will roll out in the next few days to ChatGPT users globally. Make sure to update to the latest version of the app!

(Atty from OpenAI here)

Yes! GPT-Live is much better at ignoring background noise, including other people speaking. Not perfect, but you should feel a big difference.

(Atty from OpenAI here)

Yes, GPT-Live is much better at ignoring background noise! I use it every day in the car via our CarPlay integration.

Thank you for testing and the feedback Simon!

(Atty from OpenAI here)

GPT-Live-1 is the first version of a new generation of models, and we believe the full-duplex architecture + delegation enables entirely new ways of human-AI interaction.

Would love to hear your feedback!

Hi, I work on the OpenAI API — structured outputs schemas have limitations (e.g. all fields must be required, no additional properties allowed): https://platform.openai.com/docs/guides/structured-outputs/s....

If your schema is not supported, but you still want to use the model to generate output, you would use `strict: false`. Unfortunately we cannot make `strict: true` the default because it would break existing users. We hope to make it the default in a future API version.

Great article! We've updated the OpenAI API to 403 on HTTP requests instead of redirecting.

  $ curl http://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer 123" \
  -d '{}'

  {
    "error": {
      "type": "invalid_request_error",
      "code": "http_unsupported",
      "message": "The OpenAI API is only accessible over HTTPS. Ensure the URL starts with 'https://' and not 'http://'.",
      "param": null
    }
  }

Hi there, I help design the OpenAI APIs. Would you be able to share more?

You can reply here or email me at [email protected].

(Please don't hold back; we would love to hear the pain points so we can fix them.)

Hey nl — I work at OpenAI on our API. Do you mean `tool_choice="auto"`? If so, it means the model gets to pick which tool to call. The other options are:

- `tool_choice={type: "function", function: {name: "getWeather"}}`, where the developer can force a specific tool to be called. - `tool_choice="none"`, where the developer can force the model to address the user, rather than call a tool.

If you have any other feedback, please feel free to email me at [email protected]. Thanks!

Hey swyx — I work at OpenAI on our API. Sorry the change was surprising, we definitely didn't do a great job communicating it.

To confirm, the `functions` parameter will continue to be supported.

We renamed `functions` to `tools` to better align with the naming across our products (Assistants, ChatGPT), where we support other tools like `code_interpreter` and `retrieval` in addition to `function`s.

If you have any other feedback for us, please feel free to email me at [email protected]. Thanks!

Hi te_chris — I work at OpenAI and am currently working to improve our error messages. Would you be willing to share more about what errors you find annoying? My email is [email protected] (or feel free to reply here). Thanks!

Do you have a ChatGPT Enterprise subscription purchased via our sales team? Or are you an API customer?

The former should have GPT-4 access; if not, that’s a bug, and I can look into it if you email me at [email protected].

The API and ChatGPT are separate products, and usage or credits purchased for the API do not provide paid ChatGPT access.

@dang, could we update the title to "ChatGPT can now see, hear, and speak"?

Thanks for pointing this out. Sharing with the relevant folks.

Thanks! The website is no longer active, just updated my bio.

(I'm an engineer at OpenAI)

Very sorry to hear about these issues, particularly the timeouts. Latency is top of mind for us and something we are continuing to push on. Does streaming work for your use case?

https://github.com/openai/openai-cookbook/blob/main/examples...

We definitely want to investigate these and the billing issues further. Would you consider emailing me your org ID and any request IDs (if you have them) at [email protected]?

Thank you for using the API, and really appreciate the honest feedback.

These provisions were included in the House version [0] but not in the Senate version [1], so I'm not sure if they have actually passed. Not much Twitter activity on the W visa either.

[0] https://www.congress.gov/bill/117th-congress/house-bill/4521...

[1] https://www.congress.gov/bill/117th-congress/house-bill/4521...

Hey keephand, I’m working on a project that tries to solve first party auth in a more intuitive way (and doesn’t use OAuth). I’d love to chat more. Don’t see a way to reach you in your bio; if you’re open to it, could you reach out to the email in my profile?

This report has some details: https://www.justice.gov/usao-ndca/press-release/file/1300126...