by Adam
Topology of Thought
How curiosity, physics, and looking inside neural networks revealed something unexpected about how computation organizes itself
ai-research
topology
persistent-homology
transformers
Read more
[ Blog ]
Homelab adventures, infrastructure deep-dives, and lessons learned building enterprise-grade systems on a budget
by Adam
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
backdoors
Read more
by Adam
12 Hours, 7 Layers, 1 Hard Wall: Debugging Memory on DGX Spark
A deep technical investigation into why MAX Engine allocates 117GB regardless of limits on NVIDIA DGX Spark's unified memory architecture - and why the solution doesn't exist in userspace
nvidia
dgx-spark
max-engine
cuda
Read more
by Adam
Making MAX Engine Work on NVIDIA DGX Spark: An NVML Journey
How I built an NVML library replacement to unlock GPU monitoring on Grace Blackwell unified memory architecture
nvidia
dgx-spark
nvml
cuda
Read more
by Adam
How a NoMachine Update Nuked My Desktop (Twice)
A single config file can turn your Linux desktop into an expensive paperweight. Here's how NoMachine's bundled libraries broke my system and how to fix it.
linux
homelab
nomachine
debugging
Read more
by Adam
Beyond Benchmark Gaming: Multi-Model Consensus for Genuinely Capable AI
Using agreement among frontier models (Claude, GPT-5, Gemini) as a training signal to build AI that's genuinely capable, not just benchmark-optimized
ai-training
consensus
goodhart
llm
Read more