Make WordPress published its AI guidelines: disclose AI assistance, keep contributions GPLv2-or-later, and own the code either way. Includes the AJAX save function AI keeps getting wrong and the version that passes review.
How I use Cursor, Copilot, and Claude on real client work: mapping an unfamiliar legacy codebase, moving a decade-old build stack to Vite, and getting tests that cover failure modes instead of just the happy path.
Data science still gets treated as an academic exercise. Engineering constraints, caching, timeouts and safe fallbacks are what turn a model into something you can actually run on a client site.
Nested boolean masks are hard to read and harder to debug. Cleaner ways to filter Pandas DataFrames with .query(), .isin(), .between() and the .str accessor.
Raw JSON in an embedding model spends your token budget on braces and quotes. Flattening product data into plain sentences gives the model the kind of text it was trained to read.
A notebook demo is not production. This is what sits between the two: an API contract, a container, infrastructure that suits the workload, and monitoring that catches drift before the predictions quietly go bad.
Metadata filters only take music discovery so far. How CNNs read audio as Mel-spectrograms, how contrastive learning with InfoNCE loss shapes the embeddings, and why the inference belongs outside WordPress.
Fastest-route logic says nothing about what a walk is actually like. How the StreetSense project models urban walking risk with Uber’s H3 indexing, sine and cosine time encoding, and XGBoost under a Tweedie objective.
Multi-GPU training usually stalls on communication, not compute. What nvidia-smi topo and Nsight show you about NCCL overhead, and the DDP settings I change: static graph, bucket views, PowerSGD compression and smaller buckets.
Dongxiang has almost no parallel data, so we fine-tuned Meta’s NLLB-200 instead of prompting a general model. Cleaning the bilingual corpus, checking subword fertility, registering a new language tag, and why Adafactor beat AdamW on one GPU.