All writing

124 long-form pieces on architecture, training, inference, agents and safety.

All Model Architecture19 Training & Alignment22 Inference & Serving18 Agents & Orchestration11 Reasoning & Evaluation26 Safety, Security & Governance7 Platforms & Practice21

Reasoning & Evaluation 24 min

Your Improvement Is Inside the Noise: Seeds, Nondeterminism and the Reproducibility Problem in ML

Change one bit in one weight of a ResNet and, three epochs later, test accuracy differs by more than ten points. Training is a chaotic process, so a seed is not a control variable but a draw from a distribution. Most published an…

experiment-tracking-and-reproducibility statistics determinism mlops ∑ ◫

Reasoning & Evaluation 24 min

Your Test Set Is Wrong: Label Errors, Annotator Disagreement and the Ceiling on Measured Accuracy

Human reviewers confirmed 2,916 label errors in the ImageNet validation set, and an expert audit suggests the true figure is closer to one image in five. Every benchmark score is computed against an answer key written by people w…

human-data-and-annotation evaluation benchmarks measurement ∑ ◫

Reasoning & Evaluation 14 min

Your eval pipeline is the moat, not your model choice

The model layer is commoditising and the answer flips every six months. The only durable advantage is the ability to A/B a model swap end-to-end in 48 hours and know whether it improved things for your users.

evaluation benchmarks llm-as-judge reliability

Reasoning & Evaluation 28 min

Zero-Shot Forecasting: What Time-Series Foundation Models Actually Learned

A 35-million-parameter model with no knowledge of your business can forecast your demand as well as the pipeline your team spent two quarters building. That is a real result and it is routinely misread. Pretrained forecasters lea…

time-series forecasting foundation-models zero-shot ∑ ◫

Browse by topic

All writing

Your Improvement Is Inside the Noise: Seeds, Nondeterminism and the Reproducibility Problem in ML

Your Test Set Is Wrong: Label Errors, Annotator Disagreement and the Ceiling on Measured Accuracy

Your eval pipeline is the moat, not your model choice

Zero-Shot Forecasting: What Time-Series Foundation Models Actually Learned

Tags