Mint icon.arunim.fyi

Home

❯

tags

❯

paper

paper

Jan 03, 20251 min read

Papers I’ve at least partially read, or planned to read and taken notes on or commented on.

19 items with this tag.

  • Apr 26, 2025

    Existential risk narratives about AI do not distract from its immediate harms

    • ai
  • Apr 26, 2025

    Utility Engineering

    • ai/alignment
  • Apr 26, 2025

    Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark

    • ai
  • Apr 23, 2025

    IDs for AI Systems

    • ai
  • Mar 26, 2025

    Eliciting Language Model Behaviors with Investigator Agents

    • ai/adv
  • Mar 26, 2025

    Red Teaming Language Models with Language Models

    • ai/adv
  • Mar 26, 2025

    Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

    • ai/eval
  • Mar 26, 2025

    Trading Inference-Time Compute for Adversarial Robustness

    • ai/adv
  • Mar 26, 2025

    gbrt

    • ai/adv
  • Mar 26, 2025

    gcg

    • ai/adv
  • Mar 26, 2025

    mask

    • ai/eval
  • Mar 26, 2025

    planetarium benchmark

    • ai/eval
  • Mar 26, 2025

    political persuasion and LLMs

    • ai
  • Mar 26, 2025

    tinyBenchmarks: evaluating LLMs with fewer examples

    • ai/eval
  • Mar 19, 2025

    Idiosyncrasies in Large Language Models

    • ai
  • Mar 13, 2025

    Transformers need glasses! Information over-squashing in language tasks

    • ai
  • Jan 09, 2025

    superhuman performance of a large language model on the reasoning tasks of a physician

    • ai
  • Jan 08, 2025

    large language model influence on diagnostic reasoning

    • ai
  • Jan 03, 2025

    membership inference attacks and training data proofs

    • ai

Created with Quartz v4.3.1 © 2025