331–340 of 556 posts
(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!
Does video/image input still work with these duplex models?
(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!
> Would love to hear your feedback! I'm currently on the 20 $/mo subscription and using codex meaningfully, and i'm loving this. I am considering bumping my subscription to the 100 $/month and this might be the reason i switch, BUT: i really envision me using this also through other means as well (eg: agents like openclaw/hermes) in agentic ways. Will this be supported? I can make OpenAI stuff the center of my agenti…
(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!
Can we have less terrible voices please? Nothing that sounds like a bubbly millennial. Literally anything that has gravitas.
Much better than it was before but it’s still significantly weaker than a direct chat. For example I asked “Why should LLM attention use dot product instead of cosine similarity, being that we often hear vector magnitude does not encode most of the useful information needed”? The voice response was directionally right but lacked detail and was a little hand wavy. The answer to the same question in a text chat was muc…
What I’m missing from this announcement is the capability to use connectors and tools. I don’t really get it - NONE of the frontier assistants can use tools / connectors while in voice mode - Claude, ChatGPT, Gemini, Grok. It seems so obvious: I want to be able to research stuff, pull up documents, jot down notes and do productive work while I’m talking to it, and not end voice mode whenever I need to connect to an a…
The demo video shows quite how rough around the edges this is.... Doesn't quite stop fast enough when you interrupt it. Can't find info quick enough so you have to change topic and then have it give you results later, etc. This is a move in the right direction, but there is lots of engineering still to be done!
>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.
Last night, I was using voice for the first time in a few weeks, and it interrupted me and said, a bit aggressively... "I'm going to stop you right there. Let's keep the conversation focused on the topic we were covering or a new relevant topic". I tried to probe it for why it did that, what rules it was following, and it eventually told me... "My role is to keep us focused..." and, "The behaviour you saw was my atte…
Earlier quoted context omitted.
One thing has remained constant over the last little period of time. AI boosters have zero taste.
[flagged]
And what are you doing about it?
Earlier quoted context omitted.
Star Trek computer voice model is something I have yet to encounter, and I've looked repeatedly :) It's not about a specific voice, it's the fact they managed to capture "I am a utility" perfectly in the voice. Our modern friends do not want to be thought of as a utility, but to engender trust and agency all of their own and that's a huge problem for me.
I thought to try voice cloning with dots.tts ( https://huggingface.co/spaces/rednote-hilab/dots.tts ), the result is pretty good, but likely wouldn't be fast enough to use on a quasi-realtime basis: Input clip: https://vocaroo.com/19QtEPtwTjOS Prompt text: There are 14 varieties of tomato soup available from this replicator. With rice, with vegetables, Bolian style, with pasta specify hot or chilled. Output: https://…
There's been a few studys showing that novices love LLM output that's long, but experts hate it. As an example, I've been tasked with using some agentic PM tool to write specs, and it keeps generating these huge page long outputs with "HBR voice" bolded summaries of paragraph long bulletpoints. I.e.:
> Right-size hard, and watch the one open-ended edge. Endorse the DRI's simplifications wholesale: drop the runbook-per-alert mandate (keep 1–2 diagnostic-only runbooks for the high-priority set), and ride durability on the existing weekly incident + monthly operational reviews — no new governance. The single scope-creep risk is the coverage strand (gaps are defined by absence); bound it to gaps evidenced by real, already-missed customer-facing outages, not a proactive gap hunt. Curing ownership gaps (e.g. foo-bar, no clear owner) is finite in-scope work.
There's dozens of these every iteration. I can't imagine trying to deal with that via voice, I would just zone out after the second sentence.
Earlier quoted context omitted.
Can I connect it to my skills/tools? Example case, I have a knowledge base and event log in my company. I need a brainstorm companion, which will have full access to this knowledge, can converse about it and can invoke skills/tools available in the repo.
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.
One big gap I've run into for UX is most realtime voice harnesses wait for a full response from tools, and at most support the model filling the dead air until then
It'd be a game-changer to be able to have the model start replying with partial information streamed from the tool call, then seamlessly continue with additional information.