What I Benchmarked A correct calculation can still answer the wrong question. Forty-eight...
ScopeCheck: audit the benchmark before trusting its leaderboard
Related
Testing async side effects in an LLM agent harness: tickets, retries, and exactly-once
Last week I published a 30-scenario red-team harness for AI support bots. Within two days, three...
Nemotron 3.5 Transcribe on one 32 GB Blackwell card: the prompt is your API, so test it
One deployment returns verbatim, clean or speaker-tagged text by prompt: 3 minutes in 4.4 s on 32 GB. The clean prompt still adds speaker tags.
Our customers had already told us what Siri should say
Thousands of apps run on our engine: a radio station, a sports club, a local paper, a pastry shop,...