One Word Per Intent: A Launcher That Knows Why You're Asking
Or: how a benchmark campaign’s most durable output turned out to be seven lines of shell. Somewhere around the …
JESVS
últimos posts
One Point: Measuring What Uncensoring Actually Costs a Coding Model
Or: how I tried to measure the uncensoring tax, caught my own benchmark cheating twice, and found out the real price of …
Three Agentic Coders Walked Into My 28 GB Rig
Or: how a reasoning model lost six points to my own benchmark harness, an 80B model fit into RAM that “had no …
Squeezing 2.7x More Tokens Per Second Out of Two Mismatched GPUs
Or: how I spent a weekend benchmarking local LLM inference, caught my optimization guide lying to me four times, and …
Three Bugs in a Trench Coat: How Captive Crash-Landed BMAmiga
There’s a particular silence that settles over you when an emulator bug finally gives up. Nothing dramatic happens …
Chasing the Beam: How BMAmiga's Fading Tearing Bug Died
The bug report was almost polite: “the emulator struggles with fades — from going to white to dark, it shows some …