Alex Inch
@alexinch.bsky.social
Interested in open-ended machine learning and agentic systems. Studying a DPhil on world models at Oxford Robotics.
Is it weird that I still write most of my code by hand? I only use LLMs for non-core stuff, like hparam tuning or command line parsing.
I really want to know now. How much code do you still write yourself?
January 12, 2026 at 10:54 AM
Is it weird that I still write most of my code by hand? I only use LLMs for non-core stuff, like hparam tuning or command line parsing.
Reposted by Alex Inch
Introducing DroPE: Extending Context by Dropping Positional Embeddings
We found embeddings like RoPE aid training but bottleneck long-sequence generalization. Our solution’s simple: treat them as a temporary training scaffold, not a permanent necessity.
arxiv.org/abs/2512.12167
pub.sakana.ai/DroPE
We found embeddings like RoPE aid training but bottleneck long-sequence generalization. Our solution’s simple: treat them as a temporary training scaffold, not a permanent necessity.
arxiv.org/abs/2512.12167
pub.sakana.ai/DroPE
January 12, 2026 at 4:07 AM
Introducing DroPE: Extending Context by Dropping Positional Embeddings
We found embeddings like RoPE aid training but bottleneck long-sequence generalization. Our solution’s simple: treat them as a temporary training scaffold, not a permanent necessity.
arxiv.org/abs/2512.12167
pub.sakana.ai/DroPE
We found embeddings like RoPE aid training but bottleneck long-sequence generalization. Our solution’s simple: treat them as a temporary training scaffold, not a permanent necessity.
arxiv.org/abs/2512.12167
pub.sakana.ai/DroPE
Set myself the challenge of writing a character-level transformer with only einsums in NNX. It's generating stupid bullshit but it's kind of charming, and only takes 10 minutes to train on a TPU.
December 14, 2025 at 8:31 PM
Set myself the challenge of writing a character-level transformer with only einsums in NNX. It's generating stupid bullshit but it's kind of charming, and only takes 10 minutes to train on a TPU.
Reposted by Alex Inch
Excited to announce our book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi, Yujin Tang, Risto Miikkulainen, and myself. We explore decades of work on evolving intelligent agents and shows how neuroevolution can drive creativity in deep learning, RL, LLMs and AI Agents!
November 20, 2025 at 7:22 AM
Excited to announce our book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi, Yujin Tang, Risto Miikkulainen, and myself. We explore decades of work on evolving intelligent agents and shows how neuroevolution can drive creativity in deep learning, RL, LLMs and AI Agents!