The article analyzes the loss of diagnostic power of the Turing Test in the face of the development of Large Language Models (LLMs), which can effectively imitate human conversational behaviors without possessing a human cognitive architecture. The author points to research results in which mode...
You wrote tests for your LLM feature, and they call the real model, because that feels like the honest way to test it. Say there are 100 of them, one call each, and the suite runs 30 times a working day: locally while you work, and again on every push. That's 66,000 paid calls a month.
Here is a cost calculator i made to estimate ocr cost on the main llm provider, it request the free endpoints of each llm provider and multiply by the input token price.
Madison Polidoro, a Philadelphia-based fine artist, built a remote-controlled sculpture from wood and foam in response to delivery robots.
13 points, 6 comments on Hacker News
1 points, 0 comments on Hacker News