Sakana AI

A deep dive into the judge, minifier, and prompt loop that squeeze correct solutions down to the smallest possible Python.

Sakana AI’s open-source stack turns token order into a learnable layer. The payoff is strongest when the input is messy, the signal is uneven, and rigid sequence order gets in the way.

A deep dive into the repo that couples activation sparsity with H100-tuned CUDA kernels, so the model’s zeros become real speed, lower memory use, and lower energy.

A curated Markdown map of labs, libraries, benchmarks, and learning resources shows how neuroevolution becomes usable when someone turns a field into a commons.

Sakana AI's evaluation framework asks an LLM to critique, compare, and rank translations before it ever emits a final verdict.

This research repo treats training as denoising, splits ViT into independently trainable blocks, and uses diffusion math to rethink the memory wall.

Sakana AI’s D2L skips the long prompt and generates LoRA adapters from the document itself.

A closer look at the framework that turns distributed LLM training into a plug-in architecture for data, loss functions, configs, and checkpoints.

Digital Red Queen uses an LLM to evolve Core War warriors in an adversarial loop, turning a retro programming game into a lab for open-ended adaptation.

A minimal replication of Sakana AI’s RL’s Razor experiment, where a single extra input bit, a KL-minimal oracle, and group-relative RL turn catastrophic forgetting into something you can inspect, compare, and predict.

Sakana AI's PD-NCA turns growth into an ecosystem, where multiple learners fight, adapt, and survive inside one shared dish.

Sakana AI’s repo extends pretrained models by removing positional embeddings, then recalibrating just enough to unlock longer context windows without brute-force long-context fine-tuning.

Sakana AI’s framework turns brittle agent-based modeling into repeatable experiments, with tools, memory, and a second parsing pass when models return messy output.

Sakana AI’s open-source experiment fuses product-key lookup with fast-weight updates, so an LLM can retrieve from a huge memory and revise what it remembers mid-stream.

Sakana AI’s robust-kbench turns CUDA evaluation into a robustness test, not a leaderboard trick.

Sakana AI's open-source pipeline turns phonology, grammar, lexicon, and orthography into a reproducible language build, not a one-shot prompt.

Sakana AI's framework for autonomous discovery uses "Islands of Intelligence" and a ruthless Novelty Judge to evolve programs that outperform human engineers.