))
OpenAI ChatGPT 4: Influence, Nudge, Direct, Tune | Turn the Lens Ep28
Manage episode 403521477 series 3240393
Indhold leveret af Jeff Frick. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af Jeff Frick eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.
ChatGPT busted into our consciousness less than 18 months ago, and has since vacuumed up all the headlines, sucked all the oxygen out of the room, pick your metaphor, $Billions of new investment adding fuel to a raging fire. Continuing on our exploration of the virtual, digital, and augmentations, and inspired by the very creative Yadin Porter de León, I decided to take some of my questions, right to the source, and interview OpenAI ChatGPT-4. And the specific context? I like many of you, signed up and started training our own custom version of ChatGPT, just like Sam Altman said we could at the OpenAI Developer’s conference Sept 2023. ‘Introducing GPT’s - You can now create custom versions of ChatGPT that combine instructions, extra knowledge and any combination of skills’
https://openai.com/blog/introducing-gpts
I got mine, loaded it with data, and to double-check my work, asked what it remembered learning, and the answer was…..can you say statelessness? Needless to say, I have questions. So I went to the source and interviewed ChatGPT. Full disclosure, recorded the day of the AT&T issues, for whatever reason, was having connectivity issues, so I edited out most of the ‘can you hear me now?’ But I got some great answers, and now have a better understanding of terms like Influence, Nudge, Direct, and Tune, on top of the heavy lift that goes into training one of these in the first place. An Interview with OpenAI ChatGPT 4: Influence, Nudge, Direct, Tune | Turn the Lens with Jeff Frick podcast Ep28
YouTube - Click Here
Transcript and Show Notes - Click Here
36 episoder
Del
