What Does It Mean to Align AI With Human Values? | Quanta Magazine
quantamagazine.org · 2,137 words · saved by 3 readers
Making sure our machines understand the intent behind our instructions is an important problem that requires understanding intelligence itself.
What Does It Mean to Align AI With Human Values? | Quanta Magazine Home What Does It Mean to Align AI With Human Values? Read Later Share Copied! Comments Read Later Read Later Quantized Columns What Does It Mean to Align AI With Human Values? By Melanie Mitchell December 13, 2022 Making sure our machines understand the intent behind our instructions is an important problem that requires understanding intelligence itself. Read Later James O’Brien for Quanta Magazine Introduction By Melanie Mitchell Contributing Columnist December 13, 2022 View PDF/Print Mode artificial intelligence compu
saved by
related reading
- OpenAI Launches Superalignment Taskforcethezvi.substack.com
- The Artificiality of Alignmentjoinreboot.org
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- ALIGNMENT - by vincent huang - a slice of my mindmindslice.substack.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Alignment Is Proven To Be Solvable - by SE Gygesverysane.ai
- The hot mess theory of AI misalignment: More intelligent agents behave less coherently | Jascha’s blogsohl-dickstein.github.io
- Value Alignment Is a Pseudo Conceptzilanqian.substack.com
- [2001.09768] Artificial Intelligence, Values and Alignmentarxiv.org
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
- What Is The Alignment Problem? — LessWronglesswrong.com