Dogukan Tuna
hi!! I usually go by the "dthinky!" alias, though my name is Doğukan.
>> doing research.
>>> generalization, recursive self-improvement.
>>>> speedrunning for physics superintelligence.
most interested in: automating research, physics autoresearch, scalable search space under adaptive compute, internal value functions. the goal is to accelerate what's coming and make sure it lands net positive.
excited about flourishing in a world with MAS at 100 trillion params, together.
Building Ultraresearch for physics AI autoresearch.
staring at nature · thinking about thinking machines · prob. rn making fun with fable 5 to doing comp physics & chip design
On this website:
Research
A running log of posts, experiments, and longer notes from the work. View all
- Jul 20, 2026
From Scaling to Recursively Self-Improving Research, with Just Big Agentic Computers - Apr 12, 2026
Verified Replay Distillation (VRD) recipe for continual learning in verifiable domains - Mar 25, 2026
autoresearch-mamba: Karpathy-Style Autoresearch for Mamba-2, Mamba-3, and Hybrid Mamba–Transformer MoE - Feb 1, 2026
On Compression, Computation and the Space Between
Neural Networks & New Kinds
Compression is how I think about learning. The tighter a model can compress its inputs, the more structure it has actually found. Kolmogorov complexity makes this precise — it measures the length of the shortest program that produces a given output, which turns out to be the theoretical floor for any compressor.
The Ultimate Compressor
K(X) = length of the shortest program that outputs X. For any computable compressor C and all strings X:
K(X) ≤ |C(X)| + K(C) + O(1)
via the simulation argument — run C inside a universal machine
The Catch
K(X) is uncomputable — you can never know the true shortest program. But a deep network is a finite parallel computer that approximates it with bounded resources.
Why Neural Nets are Compressors
- Neural nets can simulate arbitrary programs.
- They are small computers — circuits wired by data.
- SGD searches over the space of programs they can express.
Micro-Kolmogorov Complexity
Fix an architecture, then fit a network with SGD — the bit-length of the resulting weights is a practical proxy for description length:
minf ∈ F [ loss(f) + λ · micro-K(f) ]
micro-K(f) ≈ bit-length of weights in a fixed architecture
Shorter description length → better generalization.
I'm deeply invested in methods that make learning systems compress harder and generalize further.