Jeeves. Reasoning improves Jev-like decision models

thm•18 minutes ago

Ask Jeeves - Only took us 30 years to come full circle.

tmnstr85•10 minutes ago

this was the comment i came here for

RamblingCTO•18 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•7 minutes ago

It’s ok, one week of AI hype is now enough to close a billion-dollar term sheet with VCs.

Naitik88•13 minutes ago

what about benchmark against smaller or bigger models? 9B looks too small for llm-level decisions.

swader999•37 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.

captainbland•15 minutes ago

See if it can beat Jev's Pokémon benchmark

mxkuzn•18 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•41 minutes ago

This isn't really surprising. LLM reasoning and before that, chain of thought prompting are essentially forms of test-time compute scaling.

zerop•about 1 hour ago

Are there "good" Open source Decision models built on Gemma-4 and also trainiable on own data?

raverbashing•about 1 hour ago

Jeeves, that's a name I haven't heard in a long time...

gizajob•34 minutes ago

Personally I’m happy that after a 30 year effort and hundreds of billions spent, AskJeeves finally works as intended.

fishfasell•about 1 hour ago

If Jeeves returned as an AI chat bot it would be the most brilliant resurgence of nostalgia

grokkedit•40 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•17 minutes ago

We locked him in the basement with Clippy, Bob and BonziBuddy. Who opened the damn basement door???

alienbaby•about 1 hour 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•22 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__•32 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•19 minutes ago

That seems like the only possible way to eliminate hallucination, short of a model that is never wrong.

kjs3•16 minutes ago

force the user to decide in the end

And that's...bad?

rusk•21 minutes ago

Wait til you hear about how digital circuits work at die level

keepitwiel•about 1 hour ago

Bernoulli

user3939382•about 1 hour ago

If you want to get super pedantic about what’s happening in a transistor every digital Boolean is actually this

kevindamm•about 1 hour 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.

phplovesong•28 minutes ago

So "askjeeves" has been resurrected?

Jeeves. Reasoning improves Jev-like decision models

⚡ Community Insights

Discussion (25 Comments)Read Original on HackerNews