carter

Stacker Saloon

saloon

![](https://m.stacker.news/98840)

https://survey123.arcgis.com/share/2ec6794bfffa44f983d45eefd7c3ab9f nobody go make a false report 

![](https://m.stacker.news/98837) not mine*


What are you working on this week?

I have a little more work before I can post my SN chrome extension. Might try and get to some stained glass or something 

Politics_And_Law

J.D. Vance says immigrants will 'bankrupt' the government. The opposite is true.

npub12kfw9742tpchc0ycqphjmvxsx0t89g3d5cjfvq8cc04v8ljdgr9skszpze

It has been hypothesized that neural networks with similar architectures trained on similar
data learn shared representations relevant to the learning task. We build on this idea by
extending the conceptual framework where representations learned across models trained
on the same data can be expressed as linear combinations of a universal set of basis
features. These basis features underlie the learning task itself and remain consistent across
models, regardless of scale. From this framework, we propose the Linear Representation
Transferability (LRT) Hypothesis—that there exists an affine transformation between
the representation spaces of different models.

Linear Representation Transferability: Using Small Models to Steer Larger Ones

Is SN winning?

devs

A short history of web bots and bot detection techniques

science

There’s no such thing as a tree (phylogenetically)

There Are No New Ideas in AI… Only New Datasets

The week in AI, June 24-29, 2025

optimism

Qwen VLo: From "Understanding" the World to "Depicting" It

LLM Memory

What If We Remove Tokenization In LLMs?

Immigration raids are ensnaring innocent, legal bystanders

bitcoin

Datadog’s $65M/year customer mystery solved (It was coinbase)

We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for
representation learning on graphs. We show how Transformers can be viewed
as message passing GNNs operating on fully connected graphs of tokens, where
the self-attention mechanism capture the relative importance of all tokens w.r.t.
each-other, and positional encodings provide hints about sequential ordering or
structure

Transformers are Graph Neural Networks

Introducing Pay per crawl - Content owners can charge AI crawlers for access

Claude Code now supports hooks

Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relatively little attention in recent years. In this work, we demonstrate that NFs are more powerful than previously believed.