AI evaluation benchmarks — HeatPulse — HeatPulse

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

AI evaluation benchmarks

topic2 events

papersSEP 12 04:00 UTC

Benchmark Radar Offers Searchable Database of AI Evaluation Benchmarks

A new arXiv paper introduces Benchmark Radar, a searchable database and engine intended to help model developers locate relevant evaluations along with their datasets and code. The system also aims to make the conditions behind reported benchmark scores easier to understand. It is targeted at researchers working on large language models and other AI systems.

benchmarks/evaluation/research/llm

papersSEP 10 04:00 UTC

RAP benchmark probes how LLM research agents track shifting scientific attention

Researchers introduced RAP, a task for measuring whether large language models serving as research agents can follow changes in scholarly attention, which has been hard to assess because reviews and proposed ideas lack verifiable outcomes. The findings indicate that these models acquire evidence in ways that are biased toward the specific target they are given.

agents/llms/evaluation/benchmarks