A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by intervolz on Friday November 06, 2026 @03:40PM (#50398180)

4x lower is so mathematically awkward.

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by ant6n on Friday November 06, 2026 @03:48PM (#50398304)

So like, -3x?

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by timClicks on Friday November 06, 2026 @03:56PM (#50398406)

[delayed]

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by markcerqueira on Friday November 06, 2026 @04:26PM (#50398749)

That reads fine to me as a native-ish English speaker. What would read less awkward for you?

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by mjuarez on Friday November 06, 2026 @04:32PM (#50398806)

Like a comment on another thread, 0.25x would be the much better way to say this. It's 25% of the original value. It's also consistent: If 3x means 300% the original value, then 0.25x is 25% of the original value.

If you say 4x lower, that changes the semantics for lower than x vs higher than x, which is absurd.

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by jcelerier on Friday November 06, 2026 @05:35PM (#50399416)

> If you say 4x lower, that changes the semantics for lower than x vs higher than x, which is absurd.

where does it say in the rulebook that human languages have to have perfectly symmetric pairs of words?

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by Terr_ on Friday November 06, 2026 @09:10PM (#50400979)

[delayed]

[ Parent | on HN ]