Javascript is not enabled. This site can still works but it'll be more interactive when javascript is enabled.
loading...
Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
simianwords
15 hours ago
|
on: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
Would a bigger model be able to beat yours if some effort were put into prompt?
reply
kumama
8 hours ago
|
parent
|
next
the bigger model would still cost more :) at the same time, i see prompting as being orthogonal to post-training. i'd imagine post-training a smaller model with a better prompt would make it perform even better
reply
simianwords
4 hours ago
|
root
|
parent
yes, can you show me tasks where this is true?
reply
dkersten
13 hours ago
|
parent
At what cost though? “Beating” isn’t enough if it costs 100x or even 10x the amount.
reply