Julian Stastny

Identifiers

No identifiers captured yet.

Papers (2)

1. Removing Sandbagging in LLMs by Training with Weak Supervision cs.LG · 2026 · author #3
2. Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases cs.AI · 2026 · author #4

Mentions

No mention provenance yet.

Frequent Coauthors

• Vivek Hebbar 2 shared papers
• Aryan Bhatt 1 shared papers
• Buck Shlegeris 1 shared papers
• Emil Ryd 1 shared papers
• Eric Gan 1 shared papers
• Henning Bartsch 1 shared papers
• Joe Benton 1 shared papers