xAI publishes Biosecurity at the frontier
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Published "Biosecurity at the frontier" — describes Grok 4.6's biosecurity safeguards (refusal training, inference-time protections, behavioral controls) and cites third-party evaluation by LatchBio (BioSecBench-Refusal, BioSecBench-Surveillance). Company claims: an average of 62.1% on the refusal benchmarks, the highest among the models tested; refusal of 59.2% of adversarial tasks and completion of 64.8% of benign biology tasks. Pledges expanded pre-deployment testing, more third-party evaluation and improved post-deployment monitoring for future models
Why it matters
A case of a frontier lab publishing biosecurity refusal rates in numbers and naming an external evaluator — though it is the company's own post, and there is no independent replication
Source — Primary sources first; secondary reports are labelled “Press”
Officialx.aihttps://x.ai/news/biosafety-at-the-frontierAdded in Week 36, 2026 · See that week
On the map — ⑩ Safety, Alignment line
- Previous stopShieldstral
- This recordxAI publishes Biosecurity at the frontier
- Next stopAI misuse report