Skip to content

Lj Miranda

A collection of notes, projects, and essays.

  • By Lj Miranda
  • Based in Philippines
  • Roughly eight posts per year
  • First post on

Posts per year

Data for this chart is available in the table below
Posts per year
Year starting Posts
2022 6
2023 10
2024 2

Any gaps could be due to errors when fetching the blog’s feed.

Most recent posts

A lexical view of contrast pairs in preference datasets
Preference data is a staple in the final step of the LLM training pipeline. During RLHF, we train a reward model by showing pairs of chosen and rejected model outputs so that it can teach …
On , by LJ MIRANDA, 1,638 words
Guest lecture @ UNC Charlotte: Labeling with LLMs
A few weeks ago, I held a guest lecture in the DSBA 6188: Text Mining and Information Retrieval Class at UNC Charlotte on using large language models (LLMs) for annotation. It was fun because I …
On , by LJ MIRANDA, 1,850 words
How to set up Git and SSH when your org has enforced SAML SSO
While cloning a repository from an organization with SAML SSO, I encountered an SSH error. I’ve been using Git with SSH before, and I admit that this was new: $ git clone [email protected]:myorg/repo.git Cloning into …
On , by LJ MIRANDA, 363 words