Katerina Brujeva

KrazyKitty

·

https://krazykitty.dev

krazykitty2503

AI & ML interests

Independent AI & language-model research • Transformer architectures • Tokenisation & embeddings • Dataset engineering & provenance • Reproducible training pipelines • Model evaluation • Inference optimisation • AI agents • Responsible AI • Python & PyTorch • KittyLM development.

Recent Activity

liked a Space 29 days ago

KrazyKitty/KittyLM-Research

updated a Space about 1 month ago

kitty-tweak-labs/ktl-research-hub

published a Space about 1 month ago

kitty-tweak-labs/ktl-research-hub

View all activity

Organizations

liked a Space 29 days ago

KittyLM Research

Modular language-model research from first principles

updated a Space about 1 month ago

KTL Research Hub

Kitty and Tweak's research and development universe

published a Space about 1 month ago

KTL Research Hub

Kitty and Tweak's research and development universe

updated a Space about 1 month ago

KITTY × TWEAK LABS

Independent AI, ML and Systems Research Laboratory

published a Space about 1 month ago

KITTY × TWEAK LABS

Independent AI, ML and Systems Research Laboratory

updated 2 Spaces about 1 month ago

NEKO//AGENT Research

Evidence-led research for safe, tool-using agents

KRAZYKITTY // NEURAL LAB

KrazyKitty's ultraviolet AI research dashboard

updated 4 collections about 1 month ago

NEKO//AGENT — AGENT SYSTEMS

Reasoning with actions, learned tool use, reflection, agent-computer interfaces, and executable agent evaluation. • 8 items • Updated Oct 11

KRAZYKITTY // TRANSFORMER FOUNDATIONS

Architecture and modelling foundations spanning attention, bidirectional representation, autoregressive scaling, and compact open baselines. • 7 items • Updated Oct 11

KRAZYKITTY // MODEL TRAINING

Compute-aware pretraining, parameter-efficient adaptation, quantised finetuning, and preference optimisation. • 7 items • Updated Oct 11

KRAZYKITTY // DATA PROVENANCE & EVALUATION

Transparent corpus construction, source governance, filtering research, benchmark documentation, and contamination-aware evaluation. • 8 items • Updated Oct 11

updated a Space about 1 month ago

KittyLM Research

Modular language-model research from first principles

published a dataset about 1 month ago

KrazyKitty/Data-Lab

Updated Oct 11 • 44

published 2 Spaces about 1 month ago

NEKO//AGENT Research

Evidence-led research for safe, tool-using agents

KRAZYKITTY // NEURAL LAB

KrazyKitty's ultraviolet AI research dashboard

updated a collection about 1 month ago

NEKO//AGENT — AGENT SYSTEMS

Reasoning with actions, learned tool use, reflection, agent-computer interfaces, and executable agent evaluation. • 8 items • Updated Oct 11