Julian Skirzynski

PhD student in Computer Science @UCSD and researcher @MPI_IS. Studying interpretable AI and RL to improve people's decision making.

[Julian Skirzynski @JSkirzynski]

Do we really need to learn from our mistakes? Couldn’t we just… make optimal decisions like computers 🤖 and not make mistakes?

Well, our new work accepted in Computational Brain & Behavior journal indicates that it might be possible!
https://t.co/uFw5gwgZY2 🧵👇1/9

[Julian Skirzynski @JSkirzynski]

I recently gave a 15-min talk at #NeurIPS2025 on why "interpretable" AI doesn't automatically lead to better human decisions, and discussed my research on human-AI collaboration.

Watch here: https://t.co/PtK9oIa5Af

[Julian Skirzynski @JSkirzynski]

We’ll be presenting @FAccTConference on 06.24 at 10:45 AM during the Evaluating Explainable AI session!

Come chat with us. We would love to discuss implications for AI policy, better auditing methods, and next steps for algorithmic fairness research.

#AIFairness #xAI

[Julian Skirzynski @JSkirzynski]

Right to explanation laws assume explanations help people detect algorithmic discrimination.

But is there any evidence for that?

In our latest work w/ David Danks @berkustun, we show explanations fail to help people, even under optimal conditions.

PDF https://t.co/RlKmlzxgxN

[Julian Skirzynski @JSkirzynski]

But if they are indeed used to dispute discrimination claims, we can expect multiple failed cases due to insufficient evidence and many undetected discriminatory decisions.

Current explanation-based auditing is, therefore, fundamentally flawed, and we need additional safeguards.

[Google AI @GoogleAI]

Today we introduce an AI co-scientist system, designed to go beyond deep research tools to aid scientists in generating novel hypotheses & research strategies. Learn more, including how to join the Trusted Tester Program, at https://t.co/1eqmTTZOLr

[Kexin Huang @KexinHuang5]

🧪 Introducing POPPER: an AI agent that automates hypothesis validation by sequentially designing and executing falsification experiments with statistical rigor.

🔥POPPER matched PhD-level scientists on complex bio hypothesis validation - while reducing time by 10-fold!

🧵👇

[Hailey Joren @HaileyJoren]

✅Easy: train a model to automate a routine task
❌Hard: ensure the model is accurate with minimal human oversight

In our latest #ICLR24, we introduce a modeling paradigm for this setting

Joint w @CharlieTMarx @berkustun

PDF:https://t.co/NV8Znqz0yn
ICLR:https://t.co/iGXJlvouXM

[Berk Ustun @berkustun]

📢 Please RT 📢

I am recruiting PhD students to join my group at UCSD!

We develop methods for responsible machine learning - with a focus on fairness, interpretability, robustness, and safety.

Check out https://t.co/dZzD2z5qa1 for more information.

[The Rational Altruism Lab @RtnlAltruismLab]

@FalkLieder gave a talk on Improving #Decision_making @PennMindCORE. Here’s the recording: https://t.co/g832QQsPr1

[Sarah Schwettmann @cogconfluence]

🚨 NEW PAPER 🚨

Understanding increasingly large and complex neural networks will almost certainly require other AI models (themselves uninterpretable!)

How should we evaluate automated interpretability methods?

Introducing our new benchmark, FIND: https://t.co/cxZT86HfTQ

[Falk Lieder @FalkLieder]

I'm thrilled to announce the launch of the Rational Altruism Lab at UCLA. We strengthen the scientific foundations for motivating and enabling people to pursue highly impactful altruistic projects. Please follow @RtnlAltruismLab for our news and updates.