One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.Original article:https://openai.com/research/learning-from-human-preferencesAuthors:Dario Amodei, Paul Christiano, Alex RayA podcast by BlueDot Impact.Learn more on the AI Safety Fundamentals website.
No persons identified in this episode.
This episode hasn't been transcribed yet
Help us prioritize this episode for transcription by upvoting it.
Popular episodes get transcribed faster
Other recent transcribed episodes
Transcribed and ready to explore now
3ª PARTE | 17 DIC 2025 | EL PARTIDAZO DE COPE
01 Jan 1970
El Partidazo de COPE
Buchladen: Tipps für Weihnachten
20 Dec 2025
eat.READ.sleep. Bücher für dich
BOJ alza 25pb decennale sopra 2%, Oracle vola con accordo Tik Tok, 90 mld eurobond per Ucraina | Morning Finance
19 Dec 2025
Black Box - La scatola nera della finanza
365. The BEST advice for managing ADHD in your 20s ft. Chris Wang
19 Dec 2025
The Psychology of your 20s
LVST 19 de diciembre de 2025
19 Dec 2025
La Venganza Será Terrible (oficial)
Cuando la Ciencia Ficción Explicó el Mundo que Hoy Vivimos
19 Dec 2025
El Podcast de Marc Vidal