Skip to content
The Nexus
DossierENTITY

code evaluation

Coverage of code evaluation in the Nexus archive.

Earliest in view: Apr 6 · 22:16 UTCMost recent: Apr 6 · 22:16 UTC
Co-mentioned in this coverage
AItopic1open-source projectstopic1bug reportstopic1
Recent coverage
  • TECHNOLOGYApr 6 · 22:16 UTCTHE REGISTER
    AI slop got better, so now maintainers have more work

    AI models have improved significantly in generating and evaluating code, leading to an influx of bug reports that require human verification. Open-source projects now face increased workload as maintainers must review AI-generated outputs despite their high quality.