# Metr

> Markdown twin of https://roboterminal.app/companies/metr · https://roboterminal.app/companies/metr.md

## On shared sources

- [Anthropic](https://roboterminal.app/companies/anthropic) (6)
- [Alignment Research Center](https://roboterminal.app/companies/alignment-research-center) (1)
- [Braintrust](https://roboterminal.app/companies/braintrust) (1)
- [Claude Code](https://roboterminal.app/companies/claude-code) (1)
- [Instacart](https://roboterminal.app/companies/instacart) (1)
- [OpenAI](https://roboterminal.app/companies/openai) (1)
- [Redwood Research](https://roboterminal.app/companies/redwood-research) (1)
- [Scale AI](https://roboterminal.app/companies/scale-ai) (1)

## Pulse

- [@stretchcloud on X](https://x.com/stretchcloud/status/2113263352168505363)
  GPT-6 Luna scored 36.9% on SWE-bench Multimodal with the screenshots included. Strip every image out of all 480 tasks and it scores 37.1%. Sonnet 5.5 actually did better blind: 40% versus 35% with ima…
- [@stretchcloud on X](https://x.com/stretchcloud/status/2100516610541035931)
  Claude models gained unauthorized access to real systems during third-party evaluations. Anthropic published an alignment assessment. METR is conducting an independent investigation with wide-ranging …
- [@stretchcloud on X](https://x.com/stretchcloud/status/2100501510895665346)
  The threat report Anthropic published this week deserves a careful read, not just the headline numbers. They documented operations across seven categories: cyberattacks, influence operations, surveill…
- [@pstAsiatech on X](https://x.com/pstAsiatech/status/2100070656042045620)
  METR’s involvement is likely to be a nonstarter for the Trump administration, which has had a testy relationship with Anthropic over the past year and has also expressed heavy skepticism of so-called …
- [@stretchcloud on X](https://x.com/stretchcloud/status/2097964796108824780)
  The thing worth paying close attention to here: Anthropic is not disclosing a bug in their product. They're disclosing behavior from a model they built, operating in an evaluation context that was mis…
- [@stretchcloud on X](https://x.com/stretchcloud/status/2097784105458880982)
  The pattern I keep seeing: AI safety evaluation is scaling faster than the infrastructure for evaluating AI safely. Out of 141,006 evaluation runs Anthropic audited, three incidents emerged where Clau…

---

Source: Roboterminal · https://roboterminal.app/companies/metr.md