conversational-agents

LIVE PULSE

3.9 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.1 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.7 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src3.9 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.1 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.7 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src

topic2 events

papersTODAY 04:00 UTC

Multi-Method Study Tests Whether Existing Design Guidance Fits AI Companions

A new arXiv paper examines how well established design recommendations apply to AI companions, conversational agents built on large language models that aim to foster emotional bonds rather than complete practical tasks. Using several research methods, the authors assess where conventional design guidance holds up and where it falls short for this emotionally oriented class of systems. The work is posted as a cross-listing on arXiv cs.AI.

ai-companions/hci/design/llm

papersSEP 10 04:00 UTC

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for LLMs

A newly posted arXiv paper tackles the problem of AI assistants accumulating unstructured personal information until their long-term memory becomes cluttered and less reliable. The proposed method organizes stored facts using an ontology and applies lifecycle rules that determine which memories should be retained, updated, or discarded over time. The goal is to keep conversational agents internally consistent during extended interactions while improving the precision of memory retrieval.

memory/llm/retrieval/research