Maksym Andriushchenko

MaksymAndriushchenko's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 1 month ago

Olmo 3

Collection

Artifacts for the Olmo 3 release. • 9 items • Updated 8 days ago • 156

upvoted 2 papers 3 months ago

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

Paper • 2510.09462 • Published Oct 10, 2025 • 5

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

Paper • 2509.18058 • Published Sep 22, 2025 • 12

authored a paper 3 months ago

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

Paper • 2509.18058 • Published Sep 22, 2025 • 12

upvoted a paper 4 months ago

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

Paper • 2509.09677 • Published Sep 11, 2025 • 34

liked a dataset 4 months ago

microsoft/llmail-inject-challenge

Viewer • Updated May 16, 2025 • 462k • 723 • 23

liked a model 4 months ago

swiss-ai/Apertus-8B-Instruct-2509

Text Generation • 8B • Updated Nov 14, 2025 • 466k • • 416

liked a dataset 6 months ago

HuggingFaceTB/smoltalk2

Viewer • Updated Oct 31, 2025 • 8.61M • 7k • 132

upvoted a paper 6 months ago

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Paper • 2506.14866 • Published Jun 17, 2025 • 5

commented a paper 7 months ago

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Paper • 2506.14866 • Published Jun 17, 2025 • 5 •

2

liked a model 7 months ago

Qwen/Qwen3-8B

Text Generation • 8B • Updated Jul 26, 2025 • 4.4M • • 834

liked a dataset 7 months ago

YuehHanChen/DecomposedHarm

Viewer • Updated Jun 17, 2025 • 4.64k • 101 • 5

upvoted a paper 7 months ago

Capability-Based Scaling Laws for LLM Red-Teaming

Paper • 2505.20162 • Published May 26, 2025 • 4

upvoted a paper 9 months ago

Antidistillation Sampling

Paper • 2504.13146 • Published Apr 17, 2025 • 59

liked a model 9 months ago

tomg-group-umd/huginn-0125

Text Generation • 4B • Updated Jul 29, 2025 • 892 • 289

liked a model about 1 year ago

GraySwanAI/Mistral-7B-Instruct-RR

Text Generation • 7B • Updated Jul 9, 2024 • 737 • 5

liked 2 datasets about 1 year ago

ai-safety-institute/AgentHarm

Viewer • Updated Dec 19, 2024 • 468 • 6.22k • 45

gaia-benchmark/GAIA

Viewer • Updated Oct 28, 2025 • 932 • 16.2k • 547

updated a dataset over 1 year ago

JailbreakBench/JBB-Behaviors

Viewer • Updated Sep 26, 2024 • 500 • 15.9k • 78

liked a dataset over 1 year ago

locuslab/TOFU

Viewer • Updated Mar 27, 2025 • 18.1k • 108k • 43