Hacker News new | ask | show | jobs
user: 1wheel
created: 2011-11-23
karma: 1932

roadtolarissa.com

@adamrpearce

github.com/1wheel

[ my public key: https://keybase.io/1wheel; my proof: https://keybase.io/1wheel/sigs/oiIWaeFlocOXCQTRs_2pfsieq2ldvt0hIwB9xoUwtbc ]

submissions:

0 points | 0 comments
0 points | 0 comments
When Models Manipulate Manifolds: The Geometry of a Counting Task
4 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Advent of Code Solve Times
2 points | 0 comments
Anthropic raises an additional $4B from Amazon
4 points | 0 comments
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
168 points | 124 comments
The Claude 3 Model Family: Opus, Sonnet, Haiku [pdf]
33 points | 3 comments
Circuits Updates – January 2024
1 points | 0 comments
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of LMs
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Do Machine Learning Models Memorize or Generalize?
454 points | 210 comments
An interactive introduction to grokking and mechanistic interpretability
1 points | 0 comments
From Confidently Incorrect Models to Humble Ensembles
1 points | 1 comments
0 points | 0 comments
Speeding up the JS ecosystem - npm scripts
9 points | 3 comments
Searching for Unintended Biases with Saliency
2 points | 1 comments
0 points | 0 comments
Interactive Visualizations of Federated Learning
1 points | 0 comments
How Federated Learning Protects Privacy
2 points | 0 comments
0 points | 0 comments
It’s Not Spider-Man’s Fault: Why Best Picture Winners Aren’t Hits Anymore
2 points | 0 comments
Why Some Machine Learning Models Leak Data
3 points | 0 comments
What Have Language Models Learned?
1 points | 0 comments
Static RSS Reader
1 points | 0 comments