Dark Mode

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
ashioyajotham
Follow
Data! Data! Data!

Victor Jotham Ashioya ashioyajotham

Data! Data! Data!
Research engineering machine learning

Block or report ashioyajotham

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
ashioyajotham/README.md

Currently Working On

  • Building assistants for information synthesis and coding
  • Mechanistic interpretability
  • Quant
  • ML systems design
  • Data science

Research Interests

  • AI Safety (red-teaming, control, mech interp and alignment)
  • Foundation Models (pre-training, post-training, confabulations ["hallucinations"], scaling laws)
  • World models (video generation models, physical/embodied AI, spatial intelligence etc)

Latest Blog Posts

> Read more on Substack


GitHub Analytics

Recent GitHub Activity

Pinned Loading

  1. fingpt_trader fingpt_trader Public template

    A quant trading system platform based on FinGPT, demonstrating new applications of large pre-trained Language Models in quantitative finance.

    Python 24 8

  2. web_research_agent web_research_agent Public

    Research implementation exploring dynamic task analysis and multi-strategy synthesis in the ReAct paradigm. Demonstrates how systems can adapt their reasoning approach based on question structure w...

    Python 1 1

  3. cot-faithfulness-mech-interp cot-faithfulness-mech-interp Public

    Mechanistic analysis of Chain-of-Thought faithfulness using GPT-2 Small

    Jupyter Notebook 2

  4. greater-than-circuit greater-than-circuit Public

    Reverse engineering the circuit responsible for the "greater than" capability in a language model

    HTML

  5. eval-awareness-research eval-awareness-research Public

    Mechanistic interpretability experiments detecting "Evaluation Awareness" in LLMs - identifying if models internally represent being monitored

    Jupyter Notebook

  6. weather_forecasting_lora weather_forecasting_lora Public

    How close can LoRA get to full fine-tuning (FullFT) in terms of learning speed, performance, and compute tradeoffs? And under what conditions?

    Python