DEV Community

Ivan Zdravkov profile picture

Ivan Zdravkov

Doctoral researcher in adaptive LLMs at the Institute of Robotics, Bulgarian Academy of Sciences. Also a backend engineer with 20+ years in production. MSc in AI & Data Processing.

Location Sofia, Bulgaria Joined Joined on  Personal website https://zdravkov.info
Your model is not the product. The pipeline around it is.
izdravkov profile

Your model is not the product. The pipeline around it is.

#ai #machinelearning #programming #datascience
Comments
5 min read

Want to connect with Ivan Zdravkov?

Create an account to connect with Ivan Zdravkov. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
What the EU AI Act actually requires of a masking layer
izdravkov profile

What the EU AI Act actually requires of a masking layer

#ai #privacy #security #research
Comments
6 min read
What EWC buys you that flat L2 does not
izdravkov profile

What EWC buys you that flat L2 does not

#ai #machinelearning #research #deeplearning
Comments
5 min read
What an internal MCP server actually solves
izdravkov profile

What an internal MCP server actually solves

#ai #programming #opensource #llm
Comments
6 min read
The real trade-off between an API model and a local one
izdravkov profile

The real trade-off between an API model and a local one

#ai #llm #opensource #machinelearning
1
Comments
6 min read
The demo is the easy part
izdravkov profile

The demo is the easy part

#ai #programming #machinelearning #opensource
Comments
5 min read
Permissions that travel with the person
izdravkov profile

Permissions that travel with the person

#ai #security #programming #privacy
Comments
6 min read
The masking layer matters more than the model
izdravkov profile

The masking layer matters more than the model

#ai #privacy #security #llm
Comments 6
7 min read
LoRA on a 16 GB card: what fits and what does not
izdravkov profile

LoRA on a 16 GB card: what fits and what does not

#ai #pytorch #deeplearning #opensource
Comments
5 min read
Why I pre-register a kill-gate for every experiment
izdravkov profile

Why I pre-register a kill-gate for every experiment

#ai #research #datascience #programming
Comments
5 min read
How wrong is a model's confidence?
izdravkov profile

How wrong is a model's confidence?

#ai #machinelearning #research #datascience
Comments
5 min read
Fluency is not understanding
izdravkov profile

Fluency is not understanding

#ai #llm #nlp #research
Comments
5 min read
Detecting PII before the model sees it
izdravkov profile

Detecting PII before the model sees it

#ai #privacy #security #nlp
Comments
5 min read
Catastrophic forgetting, measured
izdravkov profile

Catastrophic forgetting, measured

#ai #machinelearning #research #deeplearning
Comments
5 min read
Blackwell quantisation on my own card
izdravkov profile

Blackwell quantisation on my own card

#ai #pytorch #deeplearning #research
Comments
5 min read
An honest look at LLM-as-a-judge
izdravkov profile

An honest look at LLM-as-a-judge

#ai #llm #research #machinelearning
Comments
5 min read
loading...