.conf25 offers hundreds of sessions led by industry experts designed to enhance your career. The event is scheduled for September 8-11, 2025 in Boston, Massachusetts.
This article demonstrates how to use the attention mechanism in a time series classification framework, specifically for classifying normal sine waves versus 'modified' (flattened) sine waves. It details the data generation, model implementation (using a bidirectional LSTM with attention), and results, achieving high accuracy.
Traceloop's observability tool for LLM applications is now generally available. The company also announced a $6.1 million seed funding round. The platform extends OpenTelemetry to provide better observability for LLM applications, offering insights into model behavior and facilitating experimentation.
Grafana Labs have launched Grafana 12, bringing significant updates to its visualisation and dashboarding platform. Several new key features are now generally available, including Git Sync, dynamic dashboards, and improvements to Drilldown. A central feature is a new collection of observability-as-code tools, designed to help teams automate observability workflows.
This paper introduces Toto, a time series forecasting foundation model with 151 million parameters, and BOOM, a large-scale benchmark for observability time series data. Toto uses a decoder-only architecture and is trained on a large corpus of observability, open, and synthetic data. Both Toto and BOOM are open-sourced under the Apache 2.0 License.
Datadog announces the release of Toto, a state-of-the-art open-weights time series foundation model, and BOOM, a new observability benchmark. Toto achieves SOTA performance on observability metrics, and BOOM provides a challenging dataset for evaluating time series models in the observability domain.
PII Guard is an LLM-powered tool that detects and manages Personally Identifiable Information (PII) in logs — designed to support data privacy and GDPR compliance. It uses the gemma:3b model running locally via Ollama.
Edge Delta announces its new MCP Server, an open standard for streamlining communication between AI models and external data sources. It enables intelligent telemetry data analysis, adaptive pipelines, and effortless cross-tool orchestration directly within your IDE.
Edge Delta’s MCP Server acts as a bridge between developer tools and the Edge Delta platform, enabling generative AI to be integrated into observability workflows. Key benefits include:
* **Instant Root Cause Analysis:** Quickly identify the causes of errors using logs, metrics, and probable root causes.
* **Adaptive Pipelines:** AI-driven suggestions for optimizing telemetry pipeline configurations.
* **Effortless Orchestration:** Seamless integration of Edge Delta anomalies with other tools like Slack and AWS KB.
The server is built on Go and requires minimal authentication (Org ID + API Token). It can be easily integrated into IDEs with a simple configuration. The author anticipates that, despite current limitations like context window size and latency, this technology represents a significant step forward, similar to the impact of early algorithmic breakthroughs.
Edge Delta’s MCP Server acts as a bridge between developer tools and the Edge Delta platform, enabling generative AI to be integrated into observability workflows. Key benefits include:
* **Instant Root Cause Analysis:** Quickly identify the causes of errors using logs, metrics, and probable root causes.
* **Adaptive Pipelines:** AI-driven suggestions for optimizing telemetry pipeline configurations.
* **Effortless Orchestration:** Seamless integration of Edge Delta anomalies with other tools like Slack and AWS KB.
The server is built on Go and requires minimal authentication (Org ID + API Token). It can be easily integrated into IDEs with a simple configuration. The author anticipates that, despite current limitations like context window size and latency, this technology represents a significant step forward, similar to the impact of early algorithmic breakthroughs.
Why developers are spinning up AI behind your back — and how to detect it. The article discusses the rise of 'Shadow AI' - developers integrating LLMs into production without approval, the risks involved, and strategies for organizations to manage it effectively.
>We’ve seen LLMs used to auto-tag infrastructure, classify alerts, generate compliance doc stubs, and spin up internal search tools on top of knowledge bases. We’ve also seen them quietly embedded into CI/CD workflows...
>We’ve seen LLMs used to auto-tag infrastructure, classify alerts, generate compliance doc stubs, and spin up internal search tools on top of knowledge bases. We’ve also seen them quietly embedded into CI/CD workflows...
vLLM Production Stack provides a reference implementation on how to build an inference stack on top of vLLM, allowing for scalable, monitored, and performant LLM deployments using Kubernetes and Helm.
