AI ALIGNMENT FORUM
AF

Robbo

Message

I'm Rob Long. I work on AI consciousness and related issues.

https://experiencemachines.substack.com/

302

Towards Evaluating AI Systems for Moral Status Using Self-Reports

TLDR: In a new paper, we explore whether we could train future LLMs to accurately answer questions about themselves. If this works, LLM self-reports may help us test them for morally relevant states like consciousness. We think it's possible to start preliminary experiments testing for moral status in language models...

Nov 16, 2023•45

Robbo

I'm Rob Long. I work on AI consciousness and related issues.

http://robertlong.online/

https://experiencemachines.substack.com/

Robbo — AI Alignment Forum

Robbo

Message

I'm Rob Long. I work on AI consciousness and related issues.

http://robertlong.online/

https://experiencemachines.substack.com/

302

Towards Evaluating AI Systems for Moral Status Using Self-Reports

Nov 16, 2023•45

Robbo

I'm Rob Long. I work on AI consciousness and related issues.

http://robertlong.online/

https://experiencemachines.substack.com/

Towards Evaluating AI Systems for Moral Status Using Self-Reports

Ethan Perez

Ethan Perez, Robbo+ 0 more

Ethan Perez, Robbo

TLDR: In a new paper, we explore whether we could train future LLMs to accurately answer questions about themselves. If this works, LLM self-reports may help us test them for morally relevant states like consciousness.

We think it's possible to start preliminary experiments testing for moral status in language models now, so if you're interested in working with us, please reach out and/or apply to the Astra fellowship or SERI MATS (deadline November 17).

Tweet thread paper summary: Link

Abstract:

As AI systems become more advanced and widely deployed, there will likely be increasing debate over whether AI systems could have conscious experiences, desires, or other states of potential moral significance. It is important to inform

... (read 288 more words →)