hi, i'm dogukan, an AI researcher focused on compute-max RL, superhuman reasoners, and rl environments. nowadays, working on a 2x stealth mode project. trying to research, learn and experiment infinitely, until achieving [superhuman level reasoning] for [redacted].

RESEARCH_LOGS

The 1000:1 Power Paradox: Why Quantum Computers Need More Energy to Cool Than Compute
Aug 09, 2025
Energetics of Allosteric Communication in Ubiquitin Revealed by Hybrid MCTS-Langevin Simulations
May 06, 2025
Revisiting Superintelligence Control Problem with Newer Extensions
Jan 22, 2025

ARCHIVE

filter_by + █
total: 10 | words: ~30,000 | est. read: ~150 min
Tensor Decompositions
Dec 31, 2024
Mixture-of-Experts Process Groups Initialization
Dec 31, 2024
Real-Time Text and Voice-Based Retrieval Augmented Generation Pipeline with Gemini 2.0 for Long Documents
Dec 25, 2024
OpenAI's Code Execution Runtime & Replicating Sandboxing Infrastructure
Jul 02, 2024
Linen Modules for Simple Long Convolutions Sequence Modeling with Log-Linear Time Complexity
Mar 20, 2024
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Mar 07, 2024
Gradient Ascent + Jax Implementation
Mar 11, 2024
Tri-RMSNorm: Yielding Speed-up for Training Stabilization
Mar 14, 2024
Enhancing Performance with C/C++ Code Execution for Langchain Agents
Jul 18, 2024
Utilizing Airflow for Planning, Scheduling, Executing and Scaling AI Agentic Workloads
May 06, 2024
video_stream.mp4mutedlive
click_to_toggle_audio | status: silent █