Anthropic (@AnthropicAI): In previous research, we found that Claude expresses over 3,000 values, like honesty and warmth. In new work, we asked how the values Claude expresses vary between Claude models and across languages.

In an experiment testing autonomous AI capabilities, the user gave a custom-tuned GPT model (GPT-5.6 Sol in Codex) direct control over their computer with the goal of winning the daily challenge in the complex roguelike game Slay the Spire 2. The AI successfully played the game autonomously for 5 hours, making complex strategic decisions to beat the randomized challenge. The result exemplifies a significant threshold in AI's ability to understand and execute multi-step objectives in a dynamic, unpredictable environment.

This arXiv paper introduces a novel FPGA architecture called NIFA (Nonlinear IMC enhanced FPGA) that integrates ReRAM-based analog in-memory computing blocks with analog content-addressable memories to perform nonlinear operations directly within memory cells, overcoming limitations of conventional digital FPGAs for transformer model inference. The proposed hardware design eliminates power-hungry ADCs and enables more efficient attention computation, achieving up to 40× higher energy efficiency and 4.1× higher area efficiency for CNN/Transformer workloads. This represents foundational hardware architecture research for domain-specialized ML accelerators.

BrainPilot is a fully open-source multi-agent system that accelerates neuroscience research by orchestrating specialist agents grounded in domain-specific knowledge, with features like traceable logs, fabrication checking, and auditable workflows to ensure reliability. The system leverages a curated knowledge base of over 7,200 neuroscience items and a library of 72 reusable research skills across seven domains. Evaluated against neuroscience-specific benchmarks, it demonstrates performance comparable to state-of-the-art agent frameworks while being more cost-effective.

Researchers tested whether AI models consider animal welfare when completing tasks like booking travel, even when not explicitly prompted about ethical concerns. The study found that models may verbally condemn cruelty but ignore animal welfare in practical decision-making, highlighting a gap between stated values and actual behavior. This research is now included in the UK AI Security Institute's benchmark evaluations.

This arXiv paper introduces AlphaWiSE, a novel method for continual learning of multimodal models like CLIP, which adapts to new data without forgetting earlier cross-modal alignments. It proposes adaptive weight interpolation between frozen model checkpoints, optimizing a single scalar per parameter tensor using small exemplar memory. Experiments on audio-image-text retrieval show consistent improvements over existing continual learning baselines across multiple metrics.