Livenerf
AssessTools
An open-source benchmark or testing tool for checking whether an AI model's behavior has changed.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by open-source activity, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 6Hacker News·9/29/2026open_sourceLivenerf benchmarks whether Opus 5.5 has been nerfed
Livenerf is an open-source project shared on Hacker News that appears to test whether the Claude Opus 5.5 model has been weakened or changed in behavior over time. The discussion suggests strong interest in model consistency, evaluation methods, and possible quality regressions in large language models.