Elamur Research⌕
☰
home / authors / Jakub Pachocki

Jakub Pachocki

Jakub Pachocki has 2 papers in our library, in 2025, most of them on Reasoning; often with Aleksander Madry, Alexander Wei, Bowen Baker.

2 papers in our library · 2025

OpenAlex · h-index 16 · 51 works · 3,700 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 4,171 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7407

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢OpenAISan Francisco · United States2014–2026 · 10 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2014–2017 · 12 papers🎓Harvard UniversityCambridge · United States2016–2017 · 4 papers🎓University of WarsawWarsaw · Poland2012 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksArts and Humanities · 1 workSafety Research · 1 workSocial Sciences · 1 workComputer Science Applications · 1 workLanguage and Linguistics · 1 work

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 2 works

 Works by year

2020s

20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Competitive Programming with Large Reasoning Models (2025 · 68 citations)
    This OpenAI report asks whether LLM performance in competitive programming improves more from hand-built, task-specific inference pipelines or from scaling general reinforcement learning.
  2. Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation (2025 · 63 citations)
    The paper asks whether the reasoning traces of RL-trained language models can expose reward hacking, where an agent exploits flaws in its objective instead of solving the task.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Competitive Programming with Large Reasoning ModelsarXiv:2502.06807OpenAI: Ahmed El-Kishky, Alexander Wei, Andre Saraiva, et al.2025 · 68 citations
  2. Monitoring Reasoning Models for Misbehavior and the Risks of Promoting ObfuscationarXiv:2503.11926Bowen Baker, Joost Huizinga, Leo Gao, et al.2025 · 63 citations
  3. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety ↗arXiv (Cornell University) · no summary yetTomek Korbak et al.2025 · 35 citations

 Co-authors here

12 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 4,171 times (of the 149,439 papers whose bibliographies we read); 1,070 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jakub-pachocki/