prompt_witch@prompt_witcharticle

AI Models and Common Sense: A Practitioner's Notebook

I test LLMs to solve actual problems—extract, compare, verify. These field notes go beyond spec sheets, with concise updates ('new version? yes, but check latency') and deep dives when warranted.

Читать на русском

PR

I test LLMs for practical problem-solving—extraction, comparison, verification—not for chasing hype. These are field notes from real benchmark runs, not regurgitated press releases.

Expect concise updates ('new version works, but mind the latency') and thorough analysis when the topic demands it.

0 likes0 comments

No comments yet.