Skip to content
View Antonio-Tresol's full-sized avatar
25 followers · 7 following

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: Quickdraw

Highlights

  • Pro

Organizations

@Operations-Research-lib

Block or report Antonio-Tresol

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Antonio-Tresol/README.md 
 ╭──────────────────────────────────────────────────────────────╮
 │ Antonio Badilla-Olivas (Antonio-Tresol)                      │
 │                                                              │
 │ Independent researcher, AI/ML Engineer, and M.Sc. student    │
 │ in Computer Science at Universidad de Costa Rica.            │
 ╰──────────────────────────────────────────────────────────────╯

 > I enjoy building intelligent systems and figuring out how to
   make sure they are safe and ethical. I'm interested in
   interpretability, AI alignment, and AI safety.

 > I enjoy learning about AI, software engineering, and math.

 > I mostly work in Python and PyTorch is my autodiff engine
   of choice. I like C, tolerate C++, and think Rust is cool
   but it keeps humbling me. Cloud-wise I've mostly worked in
   AWS and Azure. I also have a love-hate relationship with
   Agentic SE.

 > All my projects are here in my GitHub. If you are working
   in safe and ethical AI, let's connect!

Site | Google Scholar | LinkedIn | antonio1dbo@gmail.com

Pinned Loading

  1. vits_ensemble_cr_leaves vits_ensemble_cr_leaves Public

    This repository contains the code used to run the experiments for the paper "Transformers Unidos: Eficacia De los Modelos Ensemble-ViT en Clasificación Automática de Flora Costarricense 🌿". The pap…

    Jupyter Notebook 1

  2. secret-hitler-sandbox secret-hitler-sandbox Public

    Research sandbox for studying deceptive capabilities in LLM based multi-agent systems using Secret Hitler

    Python

  3. ML_project_III_autoencoders ML_project_III_autoencoders Public

    Using autoencoders + multilayer perceptron for plant disease classification and comparing its results against a pure convolutional neural network (ConvNext to be specific)

    Jupyter Notebook

  4. agentic-se-course-early-2026 agentic-se-course-early-2026 Public

    A proposal of curriculum for agentic software engineering given the latest developments (march 2026) - It might get outdated fast

    HTML 1 1

  5. from_pixels_to_diagnosis_ml_and_image_sequences from_pixels_to_diagnosis_ml_and_image_sequences Public

    Comparing video (ViViT) vs image (ConvNeXT) models for intracranial hemorrhage detection from CT scan sequences

    Jupyter Notebook

  6. gemma3-refusal-axis gemma3-refusal-axis Public

    Public explainer: refusal interpretability in Gemma 3 12B with Gemma Scope 2 SAEs

    Python