Evidence receipt / preference
Published · transcript-backedKarina Nguyen: preference
9 Feb 2025 Lenny's Podcast OpenAI researcher on why soft skills are the future of work | Karina Nguyen (Research at OpenAI, ex-Anthropic)
“And then you need to have a trade-off between what methods you want to use. And the reason why I really love relying purely on synthetic data instead of collecting data from humans is because it's much more scalable, it's cheap, less than half.”
Source trail
Everything needed to verify it.
- Speaker
- Karina Nguyen
- Attribution
- Verified speaker
- Claim type
- preference
- Recorded
- 9 Feb 2025
- Publisher
- Lenny's Podcast
Transcript context
…Oh wow. For Canvas this was like four, five months, I guess, to go from zero to one. And then you teach product managers how to build evals and maybe how do we not only ship the better feature, but how do we think longer term? What kind of cool features did you want tasks to have? I think it would be nice for tasks to be a little bit more personalized. It'd be nice to have to create tasks via voice on a mobile, right? This is how you get research roadmap right here is thinking how the feature will be developed in the future. And then from there it's like you start getting data sets. With evals, you want to make sure that goes well. And then you need to have a trade-off between what methods you want to use. And the reason why I really love relying purely on synthetic data instead of collecting data from humans is because it's much more scalable, it's cheap, less than half. You literally sample from the model and you teach the core behaviors of the models and that will generalize to all sorts of diverse coverage. And when you launch the beta feature, you learn so much from the users that you can... All your synthetic sets can be shifted in the distribution and how the users behave on the product behavior. And this is how we improve. And this is what happened with Canvass too when we launched from beta to GA. Okay. This episode is brought to you by Loom. Loom lets you your screen, your camera and your voice to share video messages easily. Record a Loom and send it out with just a link to gather feedback, add context or share an update. So now you can delete that novel link email that you were writing. Instead, you can record your screen and share your message faster. Loom can help you have fewer meetings and make the meetings that you do have much more productive. Meetings start with everyone on the same page and end early. Problem solved, time saved. We know that everyone isn't a one-take wonder when it comes to recording videos. So Loom comes with easy editing and AI features to help you record once and get back to the work that counts. Save time, align your team, stay connected and get more done with Loom. Now part of Atlassian, the makers of Jira. Try Loom for free today at Loom.com/Lenny. That's L-O-O-M.com/Lenny. Something that I want to help people understand, and I don't even 100% understand this, is what's the simplest way to understand the job of a researcher versus say a model designer and other folks involved? What's the simplest way to understand what researchers do at OpenAI?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.