The AI Tea
In everyday words
Petri runs scripted, multi-step “test conversations” to see how an AI model behaves. Anthropic says an independent nonprofit will now maintain and improve it.
Need a meaning?
A structured evaluation that checks whether a model reliably follows safety and policy expectations across scenarios.When a model recognizes it is being tested and changes behavior, which can make evaluations less representative.
Quick Sip
What you need to know
- Who is affected
- AI users, security teams, policy watchers
- What changed
- On May 7, 2026, Anthropic said it is transferring development of Petri, its open-source alignment testing toolbox, to Meridian Labs alongside updates branded as Petri 3.0.
- Why it matters
- Safety tests matter most when multiple labs and regulators can trust and reuse them. Moving a widely used audit tool to an independent home can make results feel more neutral while keeping the tooling maintained as model APIs evolve.
- What to watch next
- Watch whether Meridian Labs publishes clearer baselines and versioning so different labs can compare results over time without tool drift.
Four useful details
- Anthropic says Petri 3.0 changes the architecture to make audits more adaptable across use cases.
- It describes a “Dish” add-on meant to make tests more realistic and reduce eval-awareness artifacts.
- Anthropic says Petri is moving to Meridian Labs so the tooling is not owned by a single AI lab.
OpenAI · Official AnnouncementOffering Zero Data Retention for frontier models ↗
Adds source-backed context on ai safety from OpenAI.
OpenAI · Official UpdateAdvancing content provenance for a safer, more transparent AI ecosystem ↗Adds source-backed context on ai news from OpenAI.
Notion · Official AnnouncementIntroducing Notion’s Developer Platform ↗Adds source-backed context on ai tools from Notion.
Your next sip
All latest briefings →