Show HN: Livenerf – a benchmark for whether Opus 5.5 gets nerfed | Hacker News - But Better

Show HN: Livenerf – a benchmark for whether Opus 5.5 gets nerfed github.com

Benchmark for tracking model capability after release. - ninjahawk/livenerf

5 points•ninjahawk1•8 days ago•2 comments•

#livenerf #benchmark #nerfed #whether #opus #whether opus #gets nerfed #tracking

2 comments

_aavaa_3 days ago

If you don’t trust and are on the lookout for silent nerfing, how are you protecting against it detecting a benchmark and using the un-nerfed model?

ethan19987 days ago

I have no idea how to do it. Keep rerunning benchmarking test can be costly.

Read the full thread on Hacker News →

Related stories

Livenerf: Has Opus 5.5 been nerfed yet?github.com
Hacker News · 885 points · 1 day ago
Is Claude Opus 5.5 nerfed? A 30-day benchmark started the clockdev.to
DEV Community · 0 points · about 11 hours ago
Show HN: FAB – A benchmark for AI agents doing financial due diligencegithub.com
Hacker News · 1 points · 3 days ago
Show HN: VisionOS 27, iOS 27 object tracking demo – placing objects eyes closedgithub.com
Hacker News · 1 points · 9 days ago
I Made a Memory Benchmark as Fair as I Could. 15 Stars, 0 Runs. What's Wrong With It?dev.to
DEV Community · 7 points · 3 days ago
Show HN: Outbound benchmark calculators, no signup, no trackingprospectio.ai
Hacker News · 1 points · 10 days ago