[ Machine-Learning ]

Discover insights, tutorials, and thoughts on technology, homelab, and development.

Apr 2, 2026 10 min read

Topology of Thought

How curiosity, physics, and looking inside neural networks revealed something unexpected about how computation organizes itself

ai-research topology persistent-homology

Mar 23, 2026 15 min read

Solving the Jane Street Dormant LLM Challenge: A Systematic Approach to Backdoor Discovery

How we solved all 3 backdoored DeepSeek V3 models using SVD weight analysis, persistent homology, multi-model deliberation, and 5,000+ indexed probes

ai-research machine-learning security

Dec 18, 2025 5 min read

I Was Wrong About Self-Improving Models: Here's What I Actually Found

A follow-up to my retracted post on self-improving models. The fidelity metric improved 18% but actual performance dropped 11%. Here's what went wrong, what I learned about Goodhart's Law, and why reproducibility filtering might be the answer.

self-improvement machine-learning goodharts-law

Dec 18, 2025 7 min read

When Models Talk the Talk but Don't Walk the Walk: A Journey into LLM Behavioral Consistency

We fine-tuned a security agent to 100% skill differentiation in probing tests, but it collapsed to a single behavior in deployment. This gap led us to develop a trust diagnostic framework.

llm fine-tuning behavioral-consistency

Dec 16, 2025 9 min read

Self-Improving Models Without Labels: What I Just Proved and Why It Matters

A 7B model taught itself to generate better security commands using only its own understanding signals. No human labels, no external reward. Here's how and why it matters.

ai machine-learning self-improvement

Dec 11, 2025 11 min read

Building an Options Trading Platform with Temporal Workflows

How I use Temporal to orchestrate backtesting pipelines that process years of market data across multiple ML experts in parallel.

homelab temporal trading