The latest from the AI and MCP ecosystem, curated daily.
OpenAI introduces IH-Challenge — a training approach that teaches models to correctly prioritise instructions from trusted sources over injected or untrusted ones. Improves resistance to prompt injection and makes models more steerable by operators. Research with direct implications for building safer agentic systems.
Today's stories:
OpenAI introduces IH-Challenge — a training approach that teaches models to correctly prioritise instructions from trusted sources over injected or untrusted ones. Improves resistance to prompt injection and makes models more steerable by operators. Research with direct implications for building safer agentic systems.
Google launched Gemini Embedding 2 — their first natively multimodal embedding model, capable of embedding text, images, and mixed content into a unified vector space. Enables semantic search and RAG pipelines that work across modalities without separate embedding models per content type. A significant capability addition for developers building multimodal retrieval systems.
A comparative analysis of 16 open-source reinforcement learning libraries for LLM training — covering throughput, async rollout support, scalability, and ease of use. Cuts through the rapidly crowded RL-for-LLMs space with concrete benchmarks and recommendations for different training scales. Useful reference for teams choosing a post-training RL stack.
Hugging Face launched Storage Buckets — a new Hub feature for storing arbitrary files (datasets, checkpoints, outputs) alongside models and datasets in a unified workspace. Removes the need to use separate S3/GCS buckets for ML artefacts, keeping everything in the HF ecosystem. A practical platform improvement for teams with large training pipelines.
