Substack Reviews

Langfuse Reviews

Substack mentions (98)

• SpaceX to buy Cursor AI coding agent operator Anysphere for $60B

  The thing is, even the center of the road academics who refrain from such comparisons are noting the similarity. The MAGA movement meets the traditional defining characteristics of fascio. We can be rigid and say that only Mussolini‘s political movement can be properly be called fascist. But if we call Hitler and the Nazis fascists as well, then we open the door to any movement that meets the criteria. And Trump... - Source: Hacker News / 16 days ago

• AMA: I'm Eric Ries (The Lean Startup) & Author of New Bestseller Incorruptible

  Yes, it's much different in other countries. See https://substack.com/@doks/p-198191751. - Source: Hacker News / 22 days ago

• Show HN: Playing with genomics foundation model tutorial/explainer article

  Hi folks, I got curious about how genomics foundation models work and wrote an article explaining how they are trained + can be used. Feel free to use the following as learning resources if you wish to jump into ML for comp bio stuff, it may help: - Code: https://github.com/dillondesilva/nt-promoter-region-classification - Article/Tutorial:... - Source: Hacker News / about 1 month ago

• CBP Directive 3340-049B: Border Search of Electronic Devices

  The vast majority of people from the developed world have no problems going through any border in the developed world. Your experience is probably representative, but that's not what we're talking about. My understanding is that de facto you have no rights at all in China. The Americans take this sort of thing very seriously, which is why it's in the news and talked about. Some guy gets imprisoned for 37... - Source: Hacker News / about 1 month ago

• GitHub – DOS 1.0: Transcription of Tim Paterson's DOS Printouts

  There was never a serious claim DOS copied CP/M code. The controversy was mostly about legality of reimplementation of the API, plus some pretty vague claims about copying the design: https://substack.com/@nemanjatrifunovic/note/p-178321556. - Source: Hacker News / 2 months ago

Langfuse mentions (28)

• Strands Agents + Langfuse Evaluations

  In this project we will build a Python banking assistant agent using Strands Agents and make it observable and continuously evaluated using Langfuse — step by step. - Source: dev.to / about 3 hours ago

• Best AI Monitoring Tools in 2026: LLM, Agent, and MCP Observability Compared

  Langfuse is the open-source standard for LLM observability. It traces every LLM interaction — prompts, completions, latency, token usage, cost — and provides the tooling to debug, evaluate, and optimize LLM applications in production. Think of it as "Datadog for LLM calls" with a focus on prompt engineering workflows. - Source: dev.to / 19 days ago

• What is an LLM evaluation harness? A deep dive into lm-eval-harness

  You're monitoring production traffic. You need Langfuse / Phoenix / Helicone / Braintrust for that. Online eval is a different problem class: implicit feedback, drift detection, hallucination rates on your data, not on HellaSwag. - Source: dev.to / 29 days ago

• How to track LLM costs per customer in production

  Gateway or proxy attribution. A reverse proxy in front of the model-provider API records the request, computes the cost, and exposes per-customer breakdowns. Open-source options include Helicone, LiteLLM, Langfuse, and OpenLLMetry. Hosted equivalents serve as the AI cost observability layer for teams that want centralized visibility: LangSmith, Datadog LLM Observability, Arize Phoenix. Adds a network hop.... - Source: dev.to / about 1 month ago

• Per-user cost attribution for your AI APP

  Same approach works with Langfuse, Phoenix, Braintrust, or your existing OTel pipeline — the metadata.userId pattern is the universal part. - Source: dev.to / about 1 month ago