Luke Salamone's Blog
https://lukesalamone.github.ioA technical blog exploring machine learning, deep learning architectures, data structures, and systems programming with in-depth implementations.
Entries
-
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up discusses an approach for countering what the autho...
-
This project is a continuation of my previous autoresearch project, which optimized a reranking model to be under 10M...
-
MathJax.Hub.Config({ tex2jax: { inlineMath: [['$','$'], ['\\(','\\)']], displayMath: [['$$','$$'], ['\[','\]']], proc...
-
There are a lot of meanings of the term “model” in machine learning and machine learning-adjacent fields. Depending o...
-
Leaving the autoresearch loop going, the LLM was able to make 7.8% progress on the distillation task. I saw Andrej Ka...
-
Leaving the autoresearch loop going, the LLM was able to make 7.8% progress on the distillation task. I saw Andrej Ka...
-
TLDR: I extracted fens and stockfish evaluations for 3.9 billion chess positions. I then trained a neural network on ...
-
TLDR: I extracted fens and stockfish evaluations for 3.9 billion chess positions. I then trained a neural network on ...
-
#mapContainer1, #mapContainer2 { color: #000; } #mapContainer1 button, #mapContainer2 button { padding: 10px 14px; bo...
-
#mapContainer1, #mapContainer2 { color: #000; } #mapContainer1 button, #mapContainer2 button { padding: 10px 14px; bo...
-
MathJax.Hub.Config({ tex2jax: { inlineMath: [['$','$'], ['\\(','\\)']], displayMath: [['$$','$$'], ['\[','\]']], proc...
-
In reinforcement learning, an “agent” is an entity which can observe the world and take actions. Multi-agent setups h...
-
Let’s say that you are selling N widgets and you need to determine a price for your widgets. There are N customers, e...
-
A neural network is a type of function originally inspired by how the brain works. However, what makes it particularl...
-
I recently built a small multi-agent simulation inspired by Rick and Morty. The setup is simple: The car must neutral...
-
I recently built a small multi-agent simulation inspired by Rick and Morty. The setup is simple: The car must neutral...
-
DeepSeek R1 is a large language model which employs test-time compute to generate a response. Unlike many past decode...
-
DeepSeek R1 is a large language model which employs test-time compute to generate a response. Unlike many decoder-bas...
-
More than 30 earths could fit between the earth and the moon. Our elementary school models of the solar system really...
-
More than 30 earths could fit between the earth and the moon. Our elementary school models of the solar system really...