Hacker News new | ask | show | jobs
by uberex 2 hours ago
Funny I casually asked Gemini and it said 500k for unquantized with decent throughput.
3 comments

This is why you shouldn't believe uncritically an answer from an LLM (neither should you do for any answer from a human either though).
i asked gemini and it replied with "Error: 400 Your prompt was blocked by safety filters. Please revise and try again."
LLMs aren't discrete calcluators or estimators of things unless framed and guided to do so.