Machine learning at scale
Subscribe
Sign in
Home
Premium sub only community
Archive
Leaderboard
About
Latest
Top
Discussions
R4ec: Teaching Your Recommender LLMs to Think Twice
TLDR; The Problem: Using Large Language Models (LLMs) for recommendations with simple, one-shot prompts is like using System-1 thinking—fast but…
Nov 2
•
Ludovico Bessi
8
October 2025
Spiking Brain-Inspired LMs
Hybrid linear MoE LLM
Oct 26
•
Ludovico Bessi
6
Beyond RLHF with Rubrics as Rewards
TL;DR: The paper "Rubrics as Rewards (RaR)" introduces a framework for LLM alignment that replaces opaque preference-based reward models with…
Oct 22
•
Ludovico Bessi
5
Agent Learning from Human Feedback (ALHF)
case study directly from databricks!
Oct 19
•
Ludovico Bessi
4
Deep Dive into Claude Code post mortem
aka reading post mortem is my guilty pleasure!
Oct 15
•
Ludovico Bessi
1
Learning Facts At Scale With Active Reading
How to reliably embed knowledge into a model's parameters?
Oct 12
•
Ludovico Bessi
7
2
IntentRec: Predict user intent with multi task learning
hierarchical models for big business gains!
Oct 5
•
Ludovico Bessi
7
2
September 2025
Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
2,146 tokens/s Code Model with Discrete Diffusion
Sep 28
•
Ludovico Bessi
4
Become a Research Scientist for a day?
aka you too can become a researcher for a day (or more!)
Sep 24
•
Ludovico Bessi
2
More Than Just a Few Tokens Deep
safety alignment that's safe also on the next tokens
Sep 21
•
Ludovico Bessi
3
1
AmazonQAC: Large scale query autocomplete dataset
Datasets are important!
Sep 14
•
Ludovico Bessi
6
[Bonus] The most overloaded role: "Machine learning engineer"
let's demistify what it actually is (spoiler: no single definition)
Sep 10
•
Ludovico Bessi
6
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
