.arunim.fyi

❯

❯

ai

Mar 11, 20251 min read

Notes, readings, and writings on artificial intelligence.

31 items with this tag.

Mar 26, 2025
AI progress
Mar 26, 2025
Eliciting Language Model Behaviors with Investigator Agents
- paper
- ai/adv
Mar 26, 2025
Red Teaming Language Models with Language Models
- paper
- ai/adv
Mar 26, 2025
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
- paper
- ai/eval
Mar 26, 2025
Trading Inference-Time Compute for Adversarial Robustness
- paper
- ai/adv
Mar 26, 2025
Utility Engineering
- paper
- ai/alignment
Mar 26, 2025
gbrt
- paper
- ai/adv
Mar 26, 2025
gcg
- paper
- ai/adv
Mar 26, 2025
mask
- paper
- ai/eval
Mar 26, 2025
o1
Mar 26, 2025
planetarium benchmark
- paper
- ai/eval
Mar 26, 2025
political persuasion and LLMs
- paper
Mar 26, 2025
tinyBenchmarks: evaluating LLMs with fewer examples
- paper
- ai/eval
Mar 19, 2025
Idiosyncrasies in Large Language Models
- paper
Mar 15, 2025
deepseek
- china
Mar 13, 2025
Transformers need glasses! Information over-squashing in language tasks
- paper
Mar 11, 2025
tokenomics
- econ
Mar 11, 2025
2.18.2025 lyft
- uber
Mar 11, 2025
3.7.2025 uber
- uber
- econ
Mar 11, 2025
AI policy
- dc
- natsec
Mar 06, 2025
climate change and ai
Feb 19, 2025
re: We're Finding Out What Humans are Bad At
- blog
Feb 02, 2025
gradient obfuscation
Jan 21, 2025
re: The number 1 bottleneck to AI progress is humans
- podcast
- dwarkesh
Jan 21, 2025
re: The phony comforts of AI skepticism
- blog
Jan 21, 2025
IDs for AI Systems
- paper
Jan 09, 2025
superhuman performance of a large language model on the reasoning tasks of a physician
- paper
Jan 08, 2025
large language model influence on diagnostic reasoning
- paper
Jan 03, 2025
membership inference attacks and training data proofs
- paper
Jan 03, 2025
openai for-profit
- podcast
- openai
Jun 17, 2024
re: Mark Zuckerberg - Llama 3, Open Sourcing, etc
- podcast
- dwarkesh

Created with Quartz v4.3.1 © 2025