March 23, 2026 at 12:00 am
Comments posted to this topic are about the item Everything is the right question away
March 23, 2026 at 6:07 pm
A few days ago I read an interesting view that said:
"AI is not predictive. It is just statistical echoes of past data".
Rick
If you do a half-assed job of things, folks will ask 'why did this ass only do half the job?'
March 23, 2026 at 10:11 pm
It's a predictive engine, which can feel like a human or an oracle. However, the prediction is a statistical likelihood of what answers the question. and it's not always past data. sometimes it's combinations of past data (words) that never existed together.
April 22, 2026 at 1:16 pm
How do you measure the effectiveness of the prediction?
Does running the prompt in multiple LLMs help increase accuracy?
412-977-3526 call/text
April 22, 2026 at 2:49 pm
There isn't a good way to measure the effectiveness, mostly because the results from LLMs are not deterministic. Using multiple models is mostly to try and understand how different they are from each other and does one tend to produce more useful results.
I guess how often you feel you have success might be the measure of "accuracy"
April 22, 2026 at 4:02 pm
I have been using known lists for comparison to what the LLM is out putting. The biggest challenge is that they don't let you return enough records to be a meaningful test.
I think the idea that geocoding isn't deterministic is challenging
Coding is an entirely different story
412-977-3526 call/text
April 23, 2026 at 10:18 am
I think things are likely deterministic-ish. In the same way that
select * from lookuptable
is often deterministic. It's not unless it's
select * from lookuptable
order by modifieddate
but it can appear to be, or be close enough to be useful. Often the same, or very similar results come back from an LLM, but it's not guaranteed.
Viewing 7 posts - 1 through 7 (of 7 total)
You must be logged in to reply to this topic. Login to reply