build1 distinct publisher
A Gemma reviewer rejected 91 of the 139 triage verdicts in a one-person security loop
Half of those rejections say the same thing, that the proposing model pushed severity past the CVSS evidence it had just cited. That is a real finding about the proposer, and it still says nothing about whether a same-family reviewer would have caught it.
Publishers:dev.to
Reality
- Evidence44
- Adoption8
- Hype gap+12
- Incentives48