This work was co-led by @collect_intel
. You can read more about their plans and work on Alignment Assemblies here:
ETHICS
-
Alignment Assemblies: Collaborative Work on AI Safety
By
–
-
Ethical AI Practices: Global Leaders Shape Responsible Future
By
–
The discussions at Expand North Star 2023 are just the beginning. With global leaders and industry experts steering the conversation, the journey towards ethical AI practices that respect societal values and contribute positively is well underway!
-
AI Governance: Balancing Innovation with Responsible Global Growth
By
–
While AI offers vast developmental potential–unregulated advancements might pose risks. The goal? Harnessing AI’s power through informed governance, ensuring global tech growth is responsible and equitable.
-
UAE Oxford Partnership Advances Global AI Governance Standards
By
–
Big news at @expandnorthstar 2023: key figures, including @EMostaque
, gathered to discuss global AI regulation standards. The backdrop is the UAE’s groundbreaking partnership with Oxford University, focused on educating officials on AI governance: ↳ -
Challenges in Training Language Models for Public Opinion Alignment
By
–
Training an LM to abide by qualitative public opinions involves a large number of subjective judgment calls and technical challenges. We enumerate all of the messy challenges we encountered so others can build upon our work.
-
Public Collective Deliberation Directs AI Behavior Online
By
–
We believe our work may be one of the first instances where members of the public have collectively directed the behavior of an AI through an online deliberation process. You can read more about our research in our blog post here:
-
Public vs Private AI Constitution Comparison Analysis
By
–
Some key differences stood out: the Public constitution focused more on objectivity and impartiality, and placed a greater emphasis on accessibility, among others. You can see a comparison of the two constitutions here: https://
efficient-manatee.files.svdcdn.com/production/ima
ges/CCAI_public_comparison_2023-1.pdf?dm=1697475572
… -
Public AI Constitution Overlaps 50% With Anthropic Version
By
–
We used Polis to ask our public to deliberate on the normative values they would like AI to abide by, and then used those opinions to curate a new AI constitution. We found that the Public constitution overlapped with the Anthropic-written constitution ~50% of the time.
-
Constitutional AI reduces bias in language models
By
–
Next, we used Constitutional AI to train an LM to adhere to the principles in the collectively-designed constitution. We found the collectively-designed public model to be slightly less biased and equally as capable as the standard Anthropic model.
-
Evaluating AI Systems: Understanding Model Constitution Differences
By
–
That said, evaluating AI systems is challenging and there is more work to do to understand how to surface differences between models trained with different constitutions: