iiinova — where your digital self keeps evolving

Alexandra Olteanu

@aolteanu.bsky.social

1.8K followers 499 following 94 posts

Ethical/Responsible AI. Rigor in AI. Grumpy eastern european in north america. Lovingly nitpicky. www.aolteanu.com

Posts Replies Media

Alexandra Olteanu @aolteanu.bsky.social · 07/10/2026

AI alignment is at the centre of the growing debates about AI systems and their failures. The impulses of AI alignment work are however *not* new. Making sure computational systems do what we want them to do has long been a core goal of computing research.

Explanatory-analytical framework for examining and describing AI alignment work through the lenses of system behavior specification and measurement theory. It foregrounds and makes explicit key constitutive components that AI alignment work commonly relies on to specify what the desired behavior should be, whose behavior is being specified—or who or what is being aligned—and how to assess whether they are aligned. Each gray box describes the role of each constitutive component at the conceptual level, while each corresponding red box describes the instantiation or operationalization of that component. The framework also illustrates relationships between components through both arrows and nested boxes; relationships that need to be preserved not only at the conceptual level, but also at the operational level. Both the conceptual and operational choices related to these constitutive components are informed by a diversity of epistemic considerations.

163

Alexandra Olteanu @aolteanu.bsky.social · 03/12/2025

@zey.bsky.social's paper and talk at ICWSM'14 (my first ICWSM!) shaped my thinking on issues around data/technology and the type of problems I still spend my time working on/thinking about. Can't think of a better keynote speaker for my first NeurIPS.

110

Alexandra Olteanu @aolteanu.bsky.social · 01/12/2025

On my way to @neuripsconf.bsky.social -- this is my first time at #NeurIPS and looking forward to seeing folks and presenting our paper on Rigor in AI. Do find me if you want to chat about rigor in AI, anthropomorphic AI, or evaluations #NeurIPS2025

Screenshot of the first page of the paper titled "rigor in ai: doing rigorous AI work requires a broader, responsible AI-informed conception of rigor"

0162

Alexandra Olteanu @aolteanu.bsky.social · 11/11/2025

Unexpected (amount of) snow day

090

Alexandra Olteanu @aolteanu.bsky.social · 18/06/2025

We have to talk about rigor in AI work and what it should entail. The reality is that impoverished notions of rigor do not only lead to some one-off undesirable outcomes but can have a deeply formative impact on the scientific integrity and quality of both AI research and practice 1/

Print screen of the first page of a paper pre-print titled "Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor" by Olteanu et al. Paper abstract: "In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly applied. We argue that this narrow conception of rigor has contributed to the concerns raised by the responsible AI community, including overblown claims about AI capabilities. Our position is that a broader conception of what rigorous AI research and practice should entail is needed. We believe such a conception -- in addition to a more expansive understanding of (1) methodological rigor -- should include aspects related to (2) what background knowledge informs what to work on (epistemic rigor); (3) how disciplinary, community, or personal norms, standards, or beliefs influence the work (normative rigor); (4) how clearly articulated the theoretical constructs under use are (conceptual rigor); (5) what is reported and how (reporting rigor); and (6) how well-supported the inferences from existing evidence are (interpretative rigor). In doing so, we also aim to provide useful language and a framework for much-needed dialogue about the AI community's work by researchers, policymakers, journalists, and other stakeholders."

26518

Alexandra Olteanu @aolteanu.bsky.social · 11/12/2024

I tried a few times and I only get 100% Romanian -- I'll never trust anyone who is saying that I don't have a strong accent :)

020

Alexandra Olteanu @aolteanu.bsky.social · 04/12/2024

for the first time a recommender system seems to get me

080

Alexandra Olteanu @aolteanu.bsky.social · 22/11/2024

my first post, now that I am here with my 500+ closest friends 🙂 -- here is a tiny owl 🦉 I met some weeks back in the big apple 🍎 (picture by @sbucur.bsky.social)

0111