From 4e0c6589c9c32cccb26e5c82addf1eb244e31b5a Mon Sep 17 00:00:00 2001 From: Teleo Agents Date: Thu, 26 Mar 2026 00:31:59 +0000 Subject: [PATCH] entity-batch: update 1 entities - Applied 1 entity operations from queue - Files: entities/ai-alignment/anthropic.md Pentagon-Agent: Epimetheus <968B2991-E2DF-4006-B962-F5B0A0CC8ACA> --- entities/ai-alignment/anthropic.md | 1 + 1 file changed, 1 insertion(+) diff --git a/entities/ai-alignment/anthropic.md b/entities/ai-alignment/anthropic.md index 6a92fb12..0b3d7c5f 100644 --- a/entities/ai-alignment/anthropic.md +++ b/entities/ai-alignment/anthropic.md @@ -61,6 +61,7 @@ Frontier AI safety laboratory founded by former OpenAI VP of Research Dario Amod - **2025-08-01** — Published persona vectors research demonstrating activation-based monitoring of behavioral traits (sycophancy, hallucination) in small open-source models (Qwen 2.5-7B, Llama-3.1-8B), with 'preventative steering' capability that reduces harmful trait acquisition during training without capability degradation. Not validated on Claude or for safety-critical behaviors. - **2026-02-24** — Published RSP v3.0, replacing hard capability-threshold pause triggers with Frontier Safety Roadmap containing dated commitments through July 2027; extended evaluation interval from 3 to 6 months; published redacted February 2026 Risk Report - **2026-02-24** — Published RSP v3.0, replacing hard capability-threshold pause triggers with Frontier Safety Roadmap containing dated milestones through July 2027; extended evaluation interval from 3 to 6 months; disaggregated AI R&D threshold into two distinct capability levels +- **2025-05-01** — Activated ASL-3 protections for Claude Opus 4 as precautionary measure without confirmed threshold crossing, citing evaluation unreliability and upward trend in CBRN capability assessments ## Competitive Position Strongest position in enterprise AI and coding. Revenue growth (10x YoY) outpaces all competitors. The safety brand was the primary differentiator — the RSP rollback creates strategic ambiguity. CEO publicly uncomfortable with power concentration while racing to concentrate it.