I fed the beginning of this post into GPT-3 and it came up with these additional thoughts. I’m extremely interested in how voice interfaces can be improved with a language model like this.
Unedited GPT-3 output:
“““
I think this problem is especially bad when you have to use a specific vocabulary, and when you have to speak in a specific order. It’s not just the laggy UI, it’s the idea that your vocabulary and phrasing is not flexible. The laggy UI is an artifact of that lack of flexibility.
I don’t think it’s hard to understand how frustrating that can be.
A lot of people in the voice community are concerned with “flow”. This is the idea that the conversation should just flow, that we shouldn’t have to interrupt it to do work.
Flow can be achieved in other interfaces by turning off prompts, and putting in defaults. But it’s hard to do in voice. First, if you have to wait too long, then you are in trouble. Second, you can’t do defaults, because the only way to get the answer is to wait for the user to speak.
I think that is true. But there are ways to achieve a kind of flow, by turning off prompts and being very responsive. We don’t have to show you all the information on the screen at once. We can use highlights to let you know the computer is paying attention, or make use of non-visual modalities to let you know something happened. If we show you something on the screen, it’s because we are trying to convey something important, and you’ll be able to act on it, but we can’t expect you to act on everything.
Even with this in mind, flow is a design principle, not a technical requirement. I don’t think we should design systems that are trying to achieve flow, because it’s very hard to do. I do think we should design systems that are responsive and forgiving.
Voice systems have a unique capability: they can communicate with you without being able to see you. This is the key to being able to make an AI feel more like a person. If I could have a computer read my mind, that would be much more powerful than if it just read my words. This is the reason that voice is so compelling, and why it’s so interesting to implement it.
Flow is a principle of interaction design, and it’s about putting in a lot of work to make a system seem less work. Voice does not make interaction feel less work. In fact, voice can be the opposite. It is work. Voice requires us to work harder, and because it is so personal, we feel that more.
Voice is a more intimate interface. You are using your voice to speak to a computer.
There is a large class of problems which are better solved with a screen. I believe this to be
”””
How has nobody connected GPT-3 up to a voice interface yet? It wouldn't reveal anything new but it I think the level of conversation GPT-3 is capable of combined with actually talking to an AI would be fairly mind blowing.
Language models can take input and figure out a response. They're designed to predict words - you just set it up so they predict the response. In fact I think that's the only thing their API lets you do at the moment.
AIDungeon (https://play.aidungeon.io/) in "custom" mode lets you enter any prompt. If you go for the paid version, you can use the higher quality "Dragon" model and tweak some of the parameters.
Unedited GPT-3 output: “““ I think this problem is especially bad when you have to use a specific vocabulary, and when you have to speak in a specific order. It’s not just the laggy UI, it’s the idea that your vocabulary and phrasing is not flexible. The laggy UI is an artifact of that lack of flexibility. I don’t think it’s hard to understand how frustrating that can be. A lot of people in the voice community are concerned with “flow”. This is the idea that the conversation should just flow, that we shouldn’t have to interrupt it to do work. Flow can be achieved in other interfaces by turning off prompts, and putting in defaults. But it’s hard to do in voice. First, if you have to wait too long, then you are in trouble. Second, you can’t do defaults, because the only way to get the answer is to wait for the user to speak. I think that is true. But there are ways to achieve a kind of flow, by turning off prompts and being very responsive. We don’t have to show you all the information on the screen at once. We can use highlights to let you know the computer is paying attention, or make use of non-visual modalities to let you know something happened. If we show you something on the screen, it’s because we are trying to convey something important, and you’ll be able to act on it, but we can’t expect you to act on everything. Even with this in mind, flow is a design principle, not a technical requirement. I don’t think we should design systems that are trying to achieve flow, because it’s very hard to do. I do think we should design systems that are responsive and forgiving. Voice systems have a unique capability: they can communicate with you without being able to see you. This is the key to being able to make an AI feel more like a person. If I could have a computer read my mind, that would be much more powerful than if it just read my words. This is the reason that voice is so compelling, and why it’s so interesting to implement it. Flow is a principle of interaction design, and it’s about putting in a lot of work to make a system seem less work. Voice does not make interaction feel less work. In fact, voice can be the opposite. It is work. Voice requires us to work harder, and because it is so personal, we feel that more. Voice is a more intimate interface. You are using your voice to speak to a computer. There is a large class of problems which are better solved with a screen. I believe this to be ”””