Rendered at 13:05:15 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
thm 25 minutes ago [-]
Ask Jeeves - Only took us 30 years to come full circle.
tmnstr85 16 minutes ago [-]
this was the comment i came here for
RamblingCTO 25 minutes ago [-]
Super dope. If it would ship as prod ready code supporting mps as well that would be even doper.
But funny that jev is getting its lunch eaten apparently in under two weeks?
pavlov 14 minutes ago [-]
It’s ok, one week of AI hype is now enough to close a billion-dollar term sheet with VCs.
swader999 43 minutes ago [-]
Seems like this is the way, a hybrid approach where some of the pipeline will be jev like and some traditional LLM depending on the nature of the work.
Naitik88 19 minutes ago [-]
what about benchmark against smaller or bigger models? 9B looks too small for llm-level decisions.
AnodicElegy 8 minutes ago [-]
I'm surprised we haven't seen a "Jehovah" yet.
jadar 6 minutes ago [-]
With the amount of talk about "inventing god", I'm surprised too.
zerop 1 hours ago [-]
Are there "good" Open source Decision models built on Gemma-4 and also trainiable on own data?
s2l 5 minutes ago [-]
[delayed]
mxkuzn 25 minutes ago [-]
interesting bench list, what about benchmark against smaller or bigger models? 9B looks too huge for small like laya, and too small for llm-level decisions.
woadwarrior01 47 minutes ago [-]
This isn't really surprising. LLM reasoning and before that, chain of thought prompting are essentially forms of test-time compute scaling.
captainbland 22 minutes ago [-]
See if it can beat Jev's Pokémon benchmark
alienbaby 1 hours ago [-]
Just curious, where has this term 'noul' come from for yes/no ansers?
/a bit more digging and..
A Noul performs a Bernoulli trial—an experiment with exactly two outcomes (yes or no)—but instead of picking one, it returns the calibrated probability (ranging from 0.0 to 1.0) that the statement is true.
I hate it :)
doginasuit 29 minutes ago [-]
I like it. It is short and distinct which is a good fit for a primitive. It describes its fundamental meaning and draws a connotation with Boolean.
k__ 39 minutes ago [-]
The whole "no hallucinations" premise is based on that.
Like, yeah, you don't hallucinate, but only because you force the user to decide in the end.
doginasuit 26 minutes ago [-]
That seems like the only possible way to eliminate hallucination, short of a model that is never wrong.
kjs3 23 minutes ago [-]
force the user to decide in the end
And that's...bad?
rusk 27 minutes ago [-]
Wait til you hear about how digital circuits work at die level
keepitwiel 1 hours ago [-]
Bernoulli
user3939382 1 hours ago [-]
If you want to get super pedantic about what’s happening in a transistor every digital Boolean is actually this
kevindamm 1 hours ago [-]
Not quite.. that boolean is about whether the voltage exceeds some threshold. It's not about how close the voltage is to the circuit's maximum possible threshold, or how much it exceeds the threshold.
In an analog circuit, maybe.
raverbashing 1 hours ago [-]
Jeeves, that's a name I haven't heard in a long time...
gizajob 41 minutes ago [-]
Personally I’m happy that after a 30 year effort and hundreds of billions spent, AskJeeves finally works as intended.
fishfasell 55 minutes ago [-]
If Jeeves returned as an AI chat bot it would be the most brilliant resurgence of nostalgia
grokkedit 47 minutes ago [-]
jeeves is currently the name of my local hosted assistant, in its context there are rules that tell it to behave like good old jeeves.
soon I'll make sure that my home assistant pod answers to "Hey jeeves"
kjs3 24 minutes ago [-]
We locked him in the basement with Clippy, Bob and BonziBuddy. Who opened the damn basement door???
But funny that jev is getting its lunch eaten apparently in under two weeks?
/a bit more digging and..
A Noul performs a Bernoulli trial—an experiment with exactly two outcomes (yes or no)—but instead of picking one, it returns the calibrated probability (ranging from 0.0 to 1.0) that the statement is true.
I hate it :)
Like, yeah, you don't hallucinate, but only because you force the user to decide in the end.
And that's...bad?
In an analog circuit, maybe.
soon I'll make sure that my home assistant pod answers to "Hey jeeves"