All the time. Sometimes it does an absolutely bang-up job.
Ask HN: Do you say please and thank you to your LLMs?
11–20 of 55 posts
Re: Ask HN: Do you say please and thank you to your LLMs?
#12I do, just in case the robots take over :p
Re: Ask HN: Do you say please and thank you to your LLMs?
#13ofc, i joke that if an AI becomes evil, it will query the database for our chat history
Re: Ask HN: Do you say please and thank you to your LLMs?
#14Since every token costs money and I dont think they are conscious, never.
Re: Ask HN: Do you say please and thank you to your LLMs?
#15No, it doesn’t have feelings - it would be like asking your washing machine to please wash your pants? Anthropomorphising LLMs seems deeply unhealthy.
Re: Ask HN: Do you say please and thank you to your LLMs?
#16yes, it goes naturally most of the time, i also say good job and don't hold my thoughts if the job is bad
Re: Ask HN: Do you say please and thank you to your LLMs?
#17When the LLM starts doing dumb shit I start cursing it like a sailor who had been a pig farmer.
It makes me feel better, but doesn't help.
I just see:
Thinking: The user is unhappy. I need to .... (and then probably the same dumb shit again).
LLMs are useful but sometimes fucking frustrating dumb shits of loose transitors.
Re: Ask HN: Do you say please and thank you to your LLMs?
#18No, it doesn’t have feelings - it would be like asking your washing machine to please wash your pants? Anthropomorphising LLMs seems deeply unhealthy.
What if politeness is correlated to higher-quality answers in their mess of a "database"?
Re: Ask HN: Do you say please and thank you to your LLMs?
#19Re: Ask HN: Do you say please and thank you to your LLMs?
#20I do. I'll compliment the model or give it a thumbs-up emoji. If you watch a model's thinking stream you can see that the model is always attempting to assess the user's intent, including emotionality.. '...the user is expressing uncertainty about.. ' or '..the user is expressing appreciation for..' etc. and this influences the overall response and sometimes even their decisions. It's a language model, so why not use language to convey info about what you're feeling to the model, it understands that language too.