AI news for platform & agent engineers
Ranked brief · refreshes every 2 hours
Skill Radar · rising this week
All tracked setups →TorchTPU is an open-source project developed by Google in collaboration with Meta that provides a native PyTorch backend for Google TPUs. It enables PyTorch workloads to execute on TPU hardware with minimal code modif... Context & related coverage →
Uber has built an MCP Gateway to standardize how AI agents discover and invoke internal services across more than 800 MCP servers and 5,000 tools. The gateway separates tool registration from runtime execution and inc... Context & related coverage →
Instead of triggering tools one at a time across turns, agents are collapsing their tool catalog into a single exec(code) tool—chaining, filtering, and awaiting actions inside an isolated sandbox. Context & related coverage →
The needle-in-a-haystack (NIAH) benchmark was introduced as a test for measuring a model's ability to find small relevant facts within a very large body of input text. However, existing NIAH benchmarks each suffer fro... Context & related coverage →
Taxonomy construction is essential for knowledge-intensive NLP yet remains costly: clustering-based methods (i) need careful per-corpus tuning and yield unstable hierarchies, while LLM-based pipelines (ii) depend on e... Context & related coverage →
OpenAI’s Grid Protectors Program will work with utilities to help future compute campuses support grid reliability and protect consumer electricity costs. Context & related coverage →
Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing benchmarks predominantly assess only agreement rates, overlooking... Context & related coverage →
Large closed-source reasoning models expose only their final answers. The intermediate reasoning that produces those answers is hidden behind API surfaces, tool-call policies, and safety filters. Existing chain-of-tho... Context & related coverage →