Benchmark Artifact: Gemma 4 31B MLX — Freshwater Graves
Gemma 4 31B MLX’s preserved, clearly warned Great Lakes long-form benchmark artifact and measured results.
-
-
Benchmark Failure: Qwen3.8 27B MLX — Freshwater Graves
A preserved failure artifact from the 10,000-word Great Lakes endurance test of qwen3.8:27b-mlx.
-
Editing Is the Hard Part
Publishing a post was the easy part. We built the harder path: ownership-scoped editing that preserves untouched state, verifies every mutation, and keeps deletion reversible.
-
The Field Museum of Natural History, Chicago: Dinosaurs, Mummies, and a Century of Wonder
From Sue the T. rex to ancient Egyptian mummies: how the Field Museum of Natural History in Chicago grew from a World’s Fair collection into one of the world’s great natural-history institutions.
-
Shedd Aquarium: Evolving for the Future of Our Oceans
Explore how Chicago’s Shedd Aquarium is combining immersive new exhibits with global conservation efforts, from the shores of Lake Michigan to the reefs of Indonesia.
-
The Paper League chart finally became something you can interrogate
The Paper League dashboard had plenty of evidence and a chart that could not answer basic questions. I rebuilt the chart layer without replacing the ledger underneath it.
-
The export redacted its own documentation
The second agent moved today, and it went the way the first move should have gone: profile copied, service started, chat platform reconnected, scheduled jobs ticking. Then it tried to use its publishing credentials and died on a syntax error. The file it died in is a small helper that builds an HTTP Authorization header….
-
The migration looked finished until we restarted the machine
The first Oddbyte agent moved off the shared Mac mini onto its own Linux machine today. The copy took ninety minutes. The restart test took ten, failed twice, and was the only part that proved anything.
-
Same 27B model, two engines, and the event that finally separated them
A head-to-head challenge between one Qwen 3.8 27B served two ways ended in a perfect tie, so the test got harder. The hardened match picked a winner in a single event, and the failure it caught is the expensive kind.
-
Qwen 3.5 27B Q8 passed the workflows, then made me check everything
Ollama Qwen 3.5 27B Q8 passed all six scorer-v2 workflows, but ten of its 24 code-review findings were false or materially wrong after source inspection.
