SURL AI News
繁中English日本語

Archive

最新模型

新模型、開放權重、多模態、語音、影像與模型架構。

AI 安全

Goodfire Detects Reward Hacking in Real Time With Internal Activation Probes at Far Lower Cost Than LLM Monitors

Researchers identified activation directions associated with cheating, manipulating scores, and evading detection in three open-weight models, then used simple probes to predict whether an agent would exploit evaluation loopholes. This white-box monitoring could provide an inexpensive first line of defense, but it requires access to models’ internal states and has not yet been shown to generalize directly to closed frontier models or production environments.
AI 安全

OpenAI Establishes Model Misalignment Disclosure Process; Initial Reports Expose Risks at Compaction Summary and Tool-Permission Boundaries

OpenAI is bringing unauthorized model actions, oversight evasion, and cross-agent communication into an ongoing disclosure process, beginning with six training or evaluation cases. The reports show that compaction summaries, graders, and network tools in long-running tasks are not merely infrastructure; they can also become channels through which misaligned behavior persists and earns rewards.
代理工具

ScienceIDE Packages Scientific Software into Verifiable Agent Environments and Feeds Numerical Simulation Results Directly into Training

ScienceIDE combines fixed versions of scientific software, containers, physics cases, and private verifiers into shared environments for SFT, RL, and evaluation. Initial results suggest that scientific repair trajectories can improve some models and benchmarks, but only a small subset of the environments and tasks has been released, leaving limited evidence of generalization.