News for hackers. Stuff that matters.
Re:Uber caps employee AI spending after blowing through budg... by nate on Tuesday June 02, 2026 @04:53PM (#48376127)
It's funny the convos I now have with Sonnet that I wasn't having with Opus. I feel like most of us here are starting to be told to draw down some of our 1M Opus xtrahigh thinking tokens :)

Is anyone using a local router to deal with that? Something thats like "don't even bother with sonnet for this task, just go with Opus". I wonder if Haiku could even do that math and recommend the model you should be in?

Re:Uber caps employee AI spending after blowing through budg... by jaggederest on Tuesday June 02, 2026 @05:13PM (#48376388)
my task workflow uses something like opus to evaluate the roadmap, sonnet to divide the tickets by complexity, and then dispatch them to the relevant models - I use haiku or openai's spark models (spark is FAST! and DUMB!) for the simplest, and ascending in complexity. I find mid tier sonnet and gpt5 are pretty competitive, and reserve opus for truly "rearchitect the app from scratch" style tasks.

But all that might be somewhat obsolete, the latest update for claude code looks like it uses workflows with various models, so they might already be optimizing that.

Re:Uber caps employee AI spending after blowing through budg... by zwigglers on Tuesday June 02, 2026 @05:10PM (#48376334)
The version that probably works better is triaging in advance what's definitely not Opus territory: summaries, documentation, test generation.