Notes from the field
Insights on agentic coding tools, LLM evaluation, benchmarking, and simulation environments.
Stay tuned for future posts and releases
Subscribe via RSS
Featured Tokenflation: simple tasks consuming ever more context, reasoning, and tool calls without more useful output. We benchmarked 14 models; one answered “Hi” with 33 tool calls and an unsolicited commit.
HN BinaryAudit benchmarks AI agents using Ghidra to find backdoors in compiled binaries of real open-source servers, proxies, and network infrastructure.
Featured Connecting Claude to Ghidra via MCP to reverse engineer River Raid. A test of AI agents against 6502 assembly, memory mapping, and 80s game logic.
HN A lot of vendors pitch AI SRE. We tested 14 models across 11 programming languages; even the best ones struggle with instrumenting code with the leading open-source standard, OpenTelemetry.
HN We tested 19 LLMs on their ability to handle real-world software engineering tasks like compiling old code and cross-compiling. See how Anthropic, OpenAI, and Google models stack up in our new benchmark – CompileBench.
Featured A one-line command to diagnose server health. Uses Nix to fetch tools without sudo and an LLM to summarize the output. No installation required.
Featured Learn how to spin up Grafana in Docker in 5 real-world examples - Prometheus metrics, Loki logs, Tempo traces, and Pyroscope profiling.
Featured Discover a pragmatic approach to building Grafana dashboards more efficiently by combining the power of AI with the automation of a CLI workflow.
Featured Apache Iceberg is a powerful open table format, but has practical limitations. Learn about its challenges with small data, metadata overhead, and real-time use cases.
Featured See how a decade of artificial intelligence hype missed the mark in tooling and learn statistical tricks insiders use to spot trouble faster than alert storms.
Featured Explore the history of Grafana, a successful Kibana fork. Learn how two multibillion-dollar companies emerged from one project to compete in observability.
Featured Navigate Elasticsearch’s complex pricing with our guide. We cover subscription models, cloud vs. self-hosted options, and hidden costs to help you budget.
Featured Launch Quesma in minutes to run Kibana dashboards on ClickHouse. This guide walks you through installation, configuration, and your first project in just 3 easy steps.
Featured Discover how Quesma merges multiple SQL statements to dramatically speed up your database queries for complex dashboards.