1 A 3 O R N
1 A 3 O R N
Posts for tag "machine-learning"
2025-03-04
Towards Institutions of Inhuman Trustworthiness and Transparency
2025-03-031
LLMs Still Bad At Simple Games
2025-01-13
Within-Generation Claudes Have Similar Beliefs About Animal Suffering
2024-12-03
Double Standards and AI Pessimism
2024-09-23
On Those Undefeatable Arguments for AI Doom
2024-05-29
CA1047 Must Be Changed: Notes on Ambiguity and Compute Trends
2024-05-15
MoE and Dense Transformers Maybe Learn the Same Thing
2024-04-28
MoE and Dense Transformers Learn the Same Thing
2024-04-24
Current LLMs Apparently Cannot Play Tic-Tac-Toe in One Forward Pass
2024-02-03
Very Simple MoE Intro
2024-01-15
Layerwise Ablations on Transformers Show Funky Things
2024-01-12
Many AI Safety Orgs Have Tried to Criminalize Currently-Existing Open-Source AI
2023-11-02
Propaganda or Science: Open Source AI and Bioterrorism Risk
2023-10-21
Notes on RWKV
2023-08-11
How RetNet Works
2023-03-04
Giant Inscrutable Matrices
2023-01-24
Scaling Comes for RL, Maybe
2023-01-03
GPT-3 Can Solve Some of ARC
2022-11-26
Experiments With Algorithm Distillation, Part 1
2022-04-01
New Scaling Laws For Large Language Models
2021-11-26
Efficient Zero: How It Works
2021-09-15
Jitters No Evidence of Stupidity in RL
2021-08-20
How DeepMind's Generally Capable Agents Were Trained