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 lukethorham on Friday November 06, 2026 @03:43PM (#50398239)

I wonder if something like this is the undisclosed new approach from Anthropic that presumably has massive improvements by combining multiple models. Leveraging decision models as much as possible seems logical for extra speed and token efficiency.

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by pearcoder on Friday November 06, 2026 @03:50PM (#50398325)

they do have the 'advisor' model setting now which also plays well with this

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by 2001zhaozhao on Friday November 06, 2026 @03:53PM (#50398368)

> undisclosed new approach from Anthropic

Any source on that?

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by lukethorham on Friday November 06, 2026 @08:17PM (#50400667)

There’s a METR audit document which apparently describes various unreleased models. This is discussed in a YT video by Wes Roth. I have no firsthand knowledge about it.

[ Parent | on HN ]

Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by couldaidothis on Friday November 06, 2026 @04:03PM (#50398496)

I think OpenAI and Anthropic have both been doing similar "routing" approaches for a while. Wasn't OpenAI one of the first to have a small model start responding to you for the first several tokens so that you got an instant response while the big model became available?

Similarly, Grok has been routing to Opus internally for a little while now I think.

[ Parent | on HN ]