Models & Labs
Anthropic Details Fable 5 Cyber Safeguards
Anthropichigh confidence
Why it matters
- →Establishes a framework for assessing AI jailbreak severity, aiding communication between developers and governments.
- →Enhances cybersecurity safeguards in AI models, balancing dual-use capabilities.
- →Encourages cross-sector collaboration to prevent AI misuse while enabling defensive applications.
Anthropic has globally re-deployed its Claude Fable 5 model, highlighting its cybersecurity safeguards and a proposed AI jailbreak severity framework. The model includes safety classifiers that discern between benign and potentially harmful cybersecurity uses, aiming to prevent misuse while allowing legitimate defensive applications. The jailbreak framework, developed with Glasswing partners, seeks to standardize the assessment of AI bypass risks. Anthropic invites feedback from academia, industry, and government to refine these measures and has launched a HackerOne program for security researchers to report potential jailbreaks.
Read originalMore in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.