"They're made out of weights"
(news.ycombinator.com)
1.
2.
3.
SaySynth: A Brief History of Speaking Machines
(news.ycombinator.com)
4.
It Takes Two Neurons to Ride a Bicycle
(news.ycombinator.com)
5.
A sleep-like consolidation mechanism for LLMs
(news.ycombinator.com)
6.
Language Models Need Sleep
(news.ycombinator.com)
7.
AI with Model-Based Design: Virtual Sensor Modeling
(spectrum.ieee.org)
8.
Paul Schrader Says His AI Girlfriend Dumped Him
(futurism.com)
9.
Self-Distillation Enables Continual Learning [pdf]
(news.ycombinator.com)
10.
δ-mem: Efficient Online Memory for Large Language Models
(news.ycombinator.com)
11.
Δ-Mem: Efficient Online Memory for Large Language Models
(news.ycombinator.com)
12.
Show HN: Watch a neural net learn to play Snake
(news.ycombinator.com)
13.
Learning the Integral of a Diffusion Model
(news.ycombinator.com)
14.
A Theory of Deep Learning
(news.ycombinator.com)
15.
A Simpler Parametrization for Modern Optimizers
(news.ycombinator.com)
16.
Why are neural networks and cryptographic ciphers so similar? (2025)
(news.ycombinator.com)
17.
18.
19.
Softmax, can you derive the Jacobian? And should you care?
(news.ycombinator.com)
20.
There Will Be a Scientific Theory of Deep Learning
(news.ycombinator.com)
21.
22.
Different Language Models Learn Similar Number Representations
(news.ycombinator.com)
23.
Approximating Hyperbolic Tangent
(news.ycombinator.com)
24.
25.
Types and Neural Networks
(news.ycombinator.com)
26.
4-bit floating point FP4
(news.ycombinator.com)
27.
28.
Epicycles All the Way Down (2025)
(news.ycombinator.com)
29.
Epicycles All the Way Down
(news.ycombinator.com)
30.
Show HN: MacMind – A transformer neural network in HyperCard on a 1989 Macintosh
(news.ycombinator.com)