Astra scored 62.7% or 99.9% on ARC-AGI-3 under different harnesses. Here is what changed, what the numbers mean, and what remains unproven.
Claude formalized Fermat's Last Theorem in Lean in 11 days. Here is what the 13-million-line proof and its verification stack establish.
EvoUndo 说明能力提升不足以批准 Agent Harness 自我修改。持久变更合并前应通过状态见证、独立影响审计与反事实恢复测试。
EvoUndo shows why capability gains are insufficient for self-modifying Agent Harnesses. Require witnessed, counterfactual recovery before merge.
Fable 5.1 与 Mythos 5.1 使用相同权重、不同护栏。模型选型应联合评测能力、干预、可用结果成本与访问资格。
Fable 5.1 and Mythos 5.1 share model weights but use different safeguards. Measure capability, intervention, cost, and access together.
WikiProfile 把被归为未编码的事实，与表现出行为编码证据却难以提取的事实分开，形成更准确的事实错误诊断。
WikiProfile separates facts classified as not encoded from facts with behavioral encoding evidence that remain hard to recall.
MCP 已把 Agent 身份列为协议重点。本文区分现行授权、企业扩展、工作负载身份、委托与 DPoP 的真实成熟度。
MCP agent identity is becoming a protocol priority. This guide separates stable authorization from draft workload identity, delegation, and DPoP work.
