Building
Mythein Labs
An ultra-fast AI Superfactory for Physical R&D, focused on semiconductor manufacturing and superconducting material science.
- High-Compute RL
- Built for Scientific Research
- Multi-Physics AI infrastructure
Dogukan Tuna
I work on AI systems, RL infrastructure, CUDA kernels, multi-agent architectures and ultra-long horizon SWE and research tasks. On this site you can find my work and my open-source projects on GitHub.
Work
What I build day to day.
Founding Engineer
Manuel AI
AI for HVAC systems and energy products: error-code resolution, service-parts discovery and document understanding for field technicians.
- Applied AI
- Agent Harness
- Infrastructure
Writing
Research notes, build logs and longer pieces.
Multi-agent orchestration with Codex, borrowing Fable 5.1 and Fugu Ultra v1.1
A Codex plugin that hands one task to Claude Fable, Opus, Sonnet, Haiku, or Sakana Fugu without leaving the session, on the subscriptions already on your machine.
Accelerating HER (Heuristic Extrapolation) on CP Tensor Decomposition by 26x
A 12-line task for Sleep-Time Research (Sleep-Time Compute): two cycles, and a solver that beat our own accelerated baseline by 26x, after the system broke its own headline result twice and caught both breaks itself.
Building World's First Thermodynamic RL Engine for Fused Ising-Gibbs Sampling Kernels in CUDA
Super Turing, the engine I build at Mythein Labs: chromatic Gibbs sampling on an Ising lattice and replica-exchange annealing, fused into a CUDA kernel that is itself the RL environment step. From Maxwell's demon and p-bits to the kernel, the oracle that grades it, and the problem classes it fits.
Verified Replay Distillation (VRD) recipe for continual learning in verifiable domains
A verifier-driven continual learning recipe that combines self-generated traces, replay, and a failure-driven curriculum to learn new task families while limiting forgetting.
autoresearch-mamba: Karpathy-Style Autoresearch for Mamba-2, Mamba-3, and Hybrid Mamba–Transformer MoE
A compact, agent-driven research harness for Mamba-2, Mamba-3, and Nemotron-H-style hybrid Mamba–Transformer MoE models on MLX and CUDA.
A self-improving skill catalog for AI agents
An open-source catalog of 19 agent-maintained skills spanning autonomous research, LLM post-training, GPU/TPU programming, and accelerated computing.