If you want to get a better picture of how I think, my posts on opinions I changed (part I, part II, part III) or on Effective Altruism are a good start. You can leave anonymous feedback here and download a pdf version of the CV here.
Marius Hobbhahn
LinkedIn
Github
Twitter
Google Scholar
Work Experience
May 2023 - now: Co-founder and CEO of Apollo Research
June 2022 - April 2023: part-time research fellow for Epoch
Education
International Max-Planck Research School Tübingen, Germany
PhD with Philipp Hennig, 2020-2023 (currently writing thesis)
Topic: Making Bayesian ML fast and scalable
University of Tübingen, Germany
M.Sc., Machine Learning, 2018-2020
Grade (1.5)
Member of the German scholarship foundation (Studienstiftung) since 2017
University of Tübingen, Germany
B.Sc., Computer Science, 2016-2019
Grade: 1.7 (3.3 GPA equivalent)
University of Tübingen, Germany
B.Sc., Cognitive Science, 2015-2018
Grade: 1.8 (3.2 GPA equivalent)
Willstätter Gymnasium Nürnberg, Germany
Abitur, 2007 - 2015
Grade: 1.4 (3.6 GPA equivalent)
Research Interests
AI Safety and Alignment
Interpretability
Model evaluations
Deceptive Alignment
Miscellaneous
AI safety/alignment
- SPAR23 mentor: Mentor of 7 AI safety students for SPAR by UC Berkeley
- LTFF grantee: Received funding for independent research on AI safety from the Long-Term Future Fund (2022)
- SERI MATS scholar: Research on deceptive alignment mentored by Evan Hubinger
- Emergent Ventures grantee Explored the role of Bayesian ML for AI safety
- AI safety camp participant: Researched reflection mechanisms as an alignment target (supervised by Beth Barnes)
- AI safety mentors and mentees founder Founded a program that connects talented individuals with senior AI experts
- OpenPhil reviewer: Reviewed articles for the Open Philanthropy worldview investigations team
- Reading group participant: Participated in the AGI fundamentals reading group and in CLR's s-risks intro fellowship by
Effective Altruism
- EA Tübingen co-founder: Co-founded the Tübingen EA chapter in 2016 and co-organized until early 2022
- Writer on LessWrong and the EA Forum
- Participant/Speaker at 10+ EAG, EAGx and other EA conferences
University Debating
- My most prestigious speaker achievements include: 3x breaking ESL at EUDC, Winning Tilbury 2019 and Doxbridge 2020 (Oxford final), Winning 2 Campus Debatten and the Southern German Championship, breaking as 3rd (2018), 2nd (2019) and 1st (2020) team at the German National Championships (DDM) and being best speaker and grand finalist at the DDM 2020
- Broke at 35+ tournaments, were in the top 10 speakers 20+ times and won 10+ of them.
- Broke at 20+ tournaments as adjudicator and chaired 5+ finals. I chief-adjudicated 15+ tournaments.
- Organized 5+ tournaments and was (vice-)president of the debating club for two years.
Academia
- Lead-organizer of the ELLIS doctoral symposium in 2021. I led a team of 12 and the event had 100 participants.
- Teaching Teaching assistant for Probablistic ML (2020, 2021), Data Literacy (2021, 2022) and math summer course (2016, 2017)
- Supervisor for 3 Bachelor and 1 Master theses
- Reviewer for various conferences including ICML22 and NeurIPS22
Skills
- Languages English (C2), German (native), French (B2)
- Coding Python > R, > Julia, Java
- Machine Learning Pytorch > JAX > Tensorflow
Selected Publications
Compute Trends Across Three Eras of Machine Learning
Jaime Sevilla, Lennart Heim, Anson Ho, Tamay Besiroglu, Marius Hobbhahn, Pablo Villalobos (2022). IJCNN.
[arxiv]
[Our World in Data]
Laplace Matching for fast Approximate Inference in Generalized Linear Models
Hobbhahn, Marius and Hennig, Philipp. (2021).
[arxiv]
[code]
[blog]
Fast Predictive Uncertainty for Classification with Bayesian Deep Networks
Hobbhahn, Marius; Kristiadi, Agustinus and Hennig, Philipp. UAI 2022.
[arxiv]
[code]
[Blog post]
Other Publications
Reflection Mechanisms as an Alignment Target: A Survey
Hobbhahn, Marius, Eric Landgrebe and Elizabeth Barnes. NeurIPS ML Safety Workshop. 2022.
[paper]
Investigating Causal Understanding in LLMs
Hobbhahn, Marius, Tom Lieberum and David Seiler. NeurIPS Workshop on Causality for Real-world Impact. 2022.
[paper]
What are the Red Flags for Neural Network Suffering?
Hobbhahn, Marius and Jan Kirchner. Seeds of Science. 2022.
[paper]
Should Altruistic benchmarks be the norm in Machine Learning?
Hobbhahn, Marius; ICML2021 Workshop for Socially Responsible Machine Learning
[paper]
Sequence Classification using Ensembles of Recurrent Generative Expert Modules
Hobbhahn, Marius; Butz, Martin; Fabi, Sarah and Otte, Sebastian. ESANN (2020).
[ESANN2020 proceedings]
[code]