| ▲ | uberex 5 hours ago | |||||||
Funny I casually asked Gemini and it said 500k for unquantized with decent throughput. | ||||||||
| ▲ | stymaar 4 hours ago | parent | next [-] | |||||||
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). | ||||||||
| ||||||||
| ▲ | colinsane 3 hours ago | parent | prev | next [-] | |||||||
i asked gemini and it replied with "Error: 400 Your prompt was blocked by safety filters. Please revise and try again." | ||||||||
| ||||||||
| ▲ | j45 4 hours ago | parent | prev [-] | |||||||
LLMs aren't discrete calcluators or estimators of things unless framed and guided to do so. | ||||||||