> Please don't use this in production. Or anything important.
5 to 10 years from now, after this has worked itself deep into the npm dependency chain, we'll be lamenting how Jev-Leftpad is causing outages in critical services.
> This means the package can add between 0 and 10 spaces. If more than 10 spaces are needed, Jev has no correct option. Which feels appropriate for this project.
I'll raise a PR which uses Jev to check if the target length is beyond this range
I have to be honest. While this is obviously a smart and useful idea, it misses one of the core features of Jev: its confidence scores. Partial confidence could easily be mapped to fractional spaces, using unicode characters like U+2009: THIN SPACE. As it stands, this package is not harnessing the full power of Jev.
important to note that the "confidence" score is... maybe not what people think it is - kind of useless, and just a convenience step from the probabilities.
from the docs: "confidence is a statistic computed from the probability distribution the answer already gives you." [0] I actually encourage people to visit the docs because it has a specific page on this with a little applet to really make this clear.
What else do people think it is? If Typesafe had found a way to measure arbitrary AI results against objective reality (past, future and present) they'd either be making a killing on the stock market or working for the NRO, not publishing that as a confidence value on their API
Well I think there's an expectation that it's similar to the probability score, something that's outputted by the model itself, and so there's some level of "intelligence" (e.g. being able to recognize if the subject matter is relevant to the data it's been trained on, or as an accumulation of errors e.g. it couldn't figure out the question).
Yeah I keep getting this weird sense that Jev is kinda poorly reinventing ML. I guess the graphs don't lie and theoretically I can replace luna with it, but I don't really use luna anyway.
What is the use case for a classifier that works 90% of the time...? I feel like if I'm classifying something, I probably care enough that 90% ain't gonna cut it...
I guess the answer is just agential stuff that effectively gets double checked by the LLM in the driver seat, anyway? That tracks, though it means that jev is mostly just for the people making harnesses. Which is all of us but still!
I think the argument would be that the classifiers of classic ML can be very useful and that Jav is a geenral purpose classifier you can just use that doesn't need to be trained per-task.
I mean when you get your bloodwork done to check for an illness, the test you get will give the right result 90% of the time - and depending on the result, you doc might order more tests, which could be more expensive but no mrpe reliable than the first - but they are going to be statistically independent, and after 2 more, he can be 99.9% sure.
Which begs the question, can Jev retest until it gets the right result? Can it tell how corellated two of its results are? 90% correct makes for a wonderful iterator, but a poor oracle.
Yup, you articulated what I was trying to say but much more clearly (thanks!). I suppose I haven't tried just setting n=3 or something, but presumably the Jev docs would mention that if it were enough to get it from 1 figure to 2 (i.e. 90% -> 99%). I agree that there are places where 90% certainty can help, but it really needs to be an agential system; when a doctor runs more tests, they are experimentally engaging with empirical reality in a context-appropriate way.
I guess, in the end: I think it'll end up being fantastically useful for artificial engineers with their vastly superior ability to keep track of fine details and rapidly context switch, but fairly niche for any of us organic engineers that are left.
All that doesn't apply to low stakes stuff like games, though -- can't wait for the first truly open world game, NGL. A silver lining to the cobalt cloud?
It's funny, i actually worked with this guy (same small startup, not closely), and recognized him from that unique username on this post. It's been so long i wouldn't have had any idea if not for the oddness of the single letter username.
Instead of using Choice with criteria "space_0", "space_1"..., it could be even more elegant to use criteria names like "", " "... which could be directly inserted into response.
83 comments
[ 0.21 ms ] story [ 52.1 ms ] threadYou pad the text.
Oh, my god.
Though, again, a yet another project for a yet another "AI" to make someone else more dependent on it...
Related:
5 to 10 years from now, after this has worked itself deep into the npm dependency chain, we'll be lamenting how Jev-Leftpad is causing outages in critical services.
I'll raise a PR which uses Jev to check if the target length is beyond this range
important to note that the "confidence" score is... maybe not what people think it is - kind of useless, and just a convenience step from the probabilities.
from the docs: "confidence is a statistic computed from the probability distribution the answer already gives you." [0] I actually encourage people to visit the docs because it has a specific page on this with a little applet to really make this clear.
[0] https://docs.typesafe.ai/confidence
What is the use case for a classifier that works 90% of the time...? I feel like if I'm classifying something, I probably care enough that 90% ain't gonna cut it...
I guess the answer is just agential stuff that effectively gets double checked by the LLM in the driver seat, anyway? That tracks, though it means that jev is mostly just for the people making harnesses. Which is all of us but still!
Which begs the question, can Jev retest until it gets the right result? Can it tell how corellated two of its results are? 90% correct makes for a wonderful iterator, but a poor oracle.
I guess, in the end: I think it'll end up being fantastically useful for artificial engineers with their vastly superior ability to keep track of fine details and rapidly context switch, but fairly niche for any of us organic engineers that are left.
All that doesn't apply to low stakes stuff like games, though -- can't wait for the first truly open world game, NGL. A silver lining to the cobalt cloud?
Btw, this model also has very tiny inherent bias: https://jev-bias-analysis.stupidlabs.lol/