1wheel
Re:A Visual Introduction to Machine Learning
on Sunday March 15, 2026 @03:14PM (#47390834)
2015 was about the last year you could get away with publishing an interactive graphic with a fixed width — this made it harder do really creative/original work.
Re:A Visual Introduction to Machine Learning
on Sunday March 15, 2026 @01:50PM (#47389872)
https://visxai.io/ has a bunch more too — see the Hall of Fame section at the bottom for some of the highlights.
I also made a dozen of these a couple years ago, my two favorites:
- https://pair.withgoogle.com/explorables/fill-in-the-blank/
Re:Open-sourcing circuit tracing tools
on Thursday May 29, 2025 @05:10PM (#44130430)
It can be! Here's a circuit showing how the model processes "PCB tracing stands for" to output "printed":
https://www.neuronpedia.org/gemma-2-2b/graph?slug=pcb-tracin...
Re:.localhost Domains
on Thursday April 10, 2025 @11:56AM (#43645208)
Browsers won't use http2 unless https is on — chrome only allows six concurrent requests to the same domain if you're not using https!
Re:Ask HN: Do you know travel blogs that have animated SVG maps of the...
on Wednesday February 05, 2025 @04:46PM (#42955671)
Advent of Code Solve Times
Anthropic raises an additional $4B from Amazon
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
The Claude 3 Model Family: Opus, Sonnet, Haiku [pdf]
Circuits Updates – January 2024
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of LMs
Re:Show HN: LLMs can generate valid JSON 100% of the time
on Monday August 14, 2023 @03:21PM (#37125589)
There's also https://lmql.ai/
Re:Do Machine Learning Models Memorize or Generalize?
on Thursday August 10, 2023 @11:24AM (#37077358)
Basically just a bunch of d3 — could be cleaned up significantly, but that's hard to do while iterating and polishing the charts.
I also have a couple of little libraries for things like annotations, interleaving svg/canvas and making d3 a bit less verbose.
- https://github.com/PAIR-code/ai-explorables/tree/master/sour...
- https://1wheel.github.io/swoopy-drag/
Do Machine Learning Models Memorize or Generalize?
An interactive introduction to grokking and mechanistic interpretability
From Confidently Incorrect Models to Humble Ensembles
Re:Launch HN: Flower (YC W23) – Train AI models on distributed or sens...
on Thursday March 23, 2023 @07:11AM (#35272910)
Speeding up the JS ecosystem - npm scripts
Searching for Unintended Biases with Saliency
Re:AI Homework
on Monday December 05, 2022 @03:38PM (#33871566)
Here's an example of that with a smaller BERT model: https://pair.withgoogle.com/explorables/fill-in-the-blank/
Interactive Visualizations of Federated Learning
How Federated Learning Protects Privacy
Re:Last public payphone removed from Manhattan streets
on Friday May 27, 2022 @03:15PM (#31533669)
It’s Not Spider-Man’s Fault: Why Best Picture Winners Aren’t Hits Anymore
Why Some Machine Learning Models Leak Data
What Have Language Models Learned?
Static RSS Reader
Election Forecast Correlations
Re:Show HN: Static blog generator in about 1 KLOC
on Saturday October 17, 2020 @03:15PM (#24812392)
Mine is 60 lines of js; the markdown library does most of the work.