Does any know how much energy a GPT-3 question like this consumes? It's awfully long, and probably highly paralleled
Show HN: Chat bot powered by GPT-3
71–80 of 87 posts
Re: Show HN: Chat bot powered by GPT-3
#72Using chatbots to solve support/sales problems is like solving the problem of autonomous driving by putting a humanoid robot behind the wheel: It's unnecessary complex overhead, just stop that! If I communicate with a human, sure natural language is the way to go. If I communicate with a computer, I want clear, straight facts just one mouse click away. I don't want to text my way through the bot database, I don't wan…
I'm not sure. Using a chatbot to triage support, or perhaps even actually provide first, or even second line support, is probably going to make for a net saving at scale. even if it's slightly leaky. Would be very careful about where to use it though. You definitely wouldn't want to deploy such a product in a critical service context, without some kind of human marshal. Something comparatively trivial though. Perhaps…
Right, most T1 support is using a template or script anyway. If I was building a better chat-support system, I'd create some sort of score that predicted the likelihood a generated answer was relevant to the question asked. If the score was low enough, present the question to a human instead. The redirection to a human could even be transparent to the user. And once the human answered the question, they wouldn't need to update a knowledgebase or a template, it could just be learned by the system. This could enable a lot of efficiency, and I don't think it would hurt the level of support a user is receiving, even if only because the current human-based support is so often just the human choosing which canned-response to use anyway. Replacing T2 or T3 support is not imminent.
Re: Show HN: Chat bot powered by GPT-3
#73How’d you get an API key
Re: Show HN: Chat bot powered by GPT-3
#74> focuses on the topic at hand and cannot be maneuvered away from it Are there any non censored, non neutered, non castrated versions of GPT-3 online somewhere?
I think if you set up custom scenarios in AI Dungeon you can basically feed it whatever you like https://play.aidungeon.io/
This is GPT-3 already? So far I have failed to create a coherent story with aidungeon... Just because each sentence taken alone makes sense does not create a useful whole.
Some people made it appear as if GPT-3 would be able to practically take over the whole world.
Re: Show HN: Chat bot powered by GPT-3
#75Earlier quoted context omitted.
I think if you set up custom scenarios in AI Dungeon you can basically feed it whatever you like https://play.aidungeon.io/
This is GPT-3 already? So far I have failed to create a coherent story with aidungeon... Just because each sentence taken alone makes sense does not create a useful whole. Some people made it appear as if GPT-3 would be able to practically take over the whole world.
Its GPT-3 if you sign up and pay a monthly subsription I believe. Otherwise its GPT-2
Re: Show HN: Chat bot powered by GPT-3
#76Earlier quoted context omitted.
I'm not sure. Using a chatbot to triage support, or perhaps even actually provide first, or even second line support, is probably going to make for a net saving at scale. even if it's slightly leaky. Would be very careful about where to use it though. You definitely wouldn't want to deploy such a product in a critical service context, without some kind of human marshal. Something comparatively trivial though. Perhaps…
Right, most T1 support is using a template or script anyway. If I was building a better chat-support system, I'd create some sort of score that predicted the likelihood a generated answer was relevant to the question asked. If the score was low enough, present the question to a human instead. The redirection to a human could even be transparent to the user. And once the human answered the question, they wouldn't need…
Why would a human that isn't related to the business but working from a script perform better than an algorithm?
Serious question. If you had a line to the CEO, or someone with actual power in the organisation, then sure I understand why connecting callers there would help. Any business that does that?
Because of this reason I actually prefer (voice) chat bots over actual people. It's clear you're working against a script and you don't feel bad dealing with them.
Re: Show HN: Chat bot powered by GPT-3
#77Here's a hedge fund using GPT-3 'Dexamethasone Announcement Could Have Made Hedge Funds A Fortune — Alpha Week' https://medium.com/@492727ZED/dexamethasone-announcement-cou...
That is not what the article is about. The article is about that the hedge funds "could" have made the profit by using Vectorspace AI's services.
Hedge funds definitely made profit off of it and without Vectorspace AI's services.
Re: Show HN: Chat bot powered by GPT-3
#78Earlier quoted context omitted.
This is GPT-3 already? So far I have failed to create a coherent story with aidungeon... Just because each sentence taken alone makes sense does not create a useful whole. Some people made it appear as if GPT-3 would be able to practically take over the whole world.
Its GPT-3 if you sign up and pay a monthly subsription I believe. Otherwise its GPT-2
Re: Show HN: Chat bot powered by GPT-3
#79Earlier quoted context omitted.
Are there any non censored, ..., versions of GPT-2 online somewhere?
Unless I'm missing some subtext, yes right here: https://github.com/openai/gpt-2 To quote: > WARNING: Samples are unfiltered and may contain offensive content.
I mean, somebody hosting an instance.
Re: Show HN: Chat bot powered by GPT-3
#80Earlier quoted context omitted.
No. A legally binding contract requires "meeting of the minds", and GPT is not a legal person capable of entering into contracts. You need actual mutual agreement, not just the presence of a facsimile. You can't edit EULAs with the browser debug tools either.
So normal EULAs aren't legally binding either? I just click accept without reading or agreeing, hardly meeting with my mind.
Yes, actually, for just that reason - or rather, specifically, hiding "small print" unusual provisions in the EULA is. EULAs are only binding inasmuch as you still "sort of know" what they say.