logoalt Hacker News

michelsedghtoday at 2:26 AM3 repliesview on HN

Thanks to a Huggingface linked below, I tested it and im not impressed. prmopt: i need to contact my boss i will be late. Result: 20mins [{"name":"set_timer","arguments":{"time_human":"20 minutes"}}]. It didnt use the email tool and i tried 2-3 different ways of asking it.


Replies

fennecfoxytoday at 9:32 AM

Query: context: { "boss_email": "[email protected]", "upcoming_meetings": [{ with: "[email protected]", "time": "11:00" }] } user: i need to contact my boss i will be late, could you tell him I'll be 15 minutes late?

Output: [{"name":"send_email","arguments":{"to":"[email protected]","subject":"upcoming_meetings","body":"I'll be 15 minutes late"}},{"name":"send_email","arguments":{"to":"[email protected]","subject":"time","body":"I'll be 15 minutes late"}},{"name":"send_email","arguments":{"to":"[email protected]","subject":"time","body":"I'll be 15 minutes late"}}]

Context definitely helps. But yeah the quality of it doesn't seem to be too high. To be fair it makes you realise that not only is parameter extraction required, but also content generation (email body). Also debouncing the 3 tool calls.

Maybe under very specific circumstances/very tight harness this sort of model would be useful?

HnUser12today at 2:50 AM

Did you give it an email tool? It uses the tool it’s given. HF example only has timer tool.

show 1 reply
mahmoudimustoday at 3:08 AM

works for me:

input: i need to contact my boss i will be late. output: [{"name":"send_email","arguments":{"to":"[email protected]","subject":"Running late","body":"I will be late for the meeting."}}]

it did have the send_email tool on the left hand side though

show 2 replies