Latent Sparse Attention (LSA) from Prefrontal AI and ETH Zurich clusters keys to speed long-context LLM inference, cutting 10M-token time to first token by over 9 times
Google's EnvHarness adapts existing agent training environments based on failure patterns, boosting ALFWorld held-out task success by nine percentage points
Timestral's largest model has 209 million parameters and leads three pretrained, zero-shot forecasting benchmarks. The smallest forecasts 96 steps from 2,048 observations in 17 milliseconds on eight CPU threads.
Prompt filters and borrowed human tokens don't hold up once agents reach production. Ory Agent Security splits the problem in two: authorize every tool call inside the agent loop, and give every deployed runtime its own machine identity.