Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
Court interpreting quality is checked by sampling.
-
Over the last two days, mostly from my phone, I’ve directed Claude through standing up a new AWS organisation, a sandboxed member account, a permissions-bounded identity for itself, and then a working AI demo on top: a court-interpretation quality tool wi…
-
Traceability problems seem to follow me around.
-
NB: Methodology, raw scores and code are all open here: github.com/rorads/open-web-analysis.
-
NB: The research bundle behind this lives here: github.com/rorads/open-web-analysis – frozen rubric, raw evidence, scoring code and figures.
-
The Problem I’m writing this from Japan, where I’ve been working mostly from my phone via Claude Code.
-
TL;DR Use the real models direct from the people who train them.
-
NB: Code can be found here: https://github.com/rorads/iati-graph-from-pg A long time ago, I worked in the Department for International Development (as it then was).
-
Back in the Day We Had Music Collections… Repo here for the impatient… Remember when you used to download your music, or even rip albums from CDs and “borrow” USB sticks?
-
What I Built I built this quantum art exhibition site in about a day, mostly by directing AI agents to do the heavy lifting.