Top all-time · #4718
Arize AI
Company blog · arize.com/blogaidata
Arize AI is the company blog at arize.com, writing about ai and data. Since 2021, 16 different Hacker News readers have linked it 16 times, most often “Claude.md: Best Practices for Optimizing with Prompt Learning”. It is still writing: the last post was on 2026-10-30, and you can follow it by feed.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
HN readers link Arize's blog for posts on LLM and ML observability, such as tracing Claude Code runs with OpenInference and Arize-Phoenix, plus a lighter overview of recent AI developments.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Continuously improve AI agents with agent observability, evaluation, tracing, and experimentation.
Most-linked posts?
- Claude.md: Best Practices for Optimizing with Prompt Learning2 people · 2 mentions · first linked 2025-11-21
- /2 people · 2 mentions · first linked 2022-12-30
- /blog/claude-code-observability-and-tracing-introducing-dev-agent-lens/2 people · 2 mentions · first linked 2025-08-22
What Hacker News says?
On reflection this thread is pretty clearly of general interest and my comment was more jargon that language, I hang out in ML zones too much. For a broad introduction to the field Karpathy's YouTube series is about as good as it gets. If you've got a pretty solid grasp of attention architectures and want a lively overview of stuff that's gone from secret to a huge deal recently I like this treatment as a light but…
Comment linking /blog/mistral-ai
on “ChatGPT for Teams”Submitted AI Ethical Issues Unraveled as a story · 4 points
HN discussion- nl · 2024-09-06
> building LLMs is very costly, and that will probably remain so for quite some time. Building LLMs is dropping in cost quickly. Back in mid 2023 training an 7B model had already dropped to $30K and it's even cheaper now. > I think it is equally likely that LLMs will perform worse in the future, because of copyright reasons and increased privacy awareness, leading to less diverse data sets to train on. I'll bet a lo…
Comment linking /resource/mosaicml/
on “Show HN: AnythingLLM – Open-Source, All-in-One Desktop AI Assistant” Submitted Building a self-improving agent on a context graph of human disagreement as a story · 3 points
HN discussionAnd yet it's a major part of the overall concept of being responsible with our use of AIs. Throwing our hands up in the air and prematurely declaring defeat is not an option long term. It's a non-starter for no other reason than potential copyright infringement means the government becomes involved, and they will stomp on the AI mouse with the force of an elephant - the opinions of amateurs and the anti-copyright mo…
Comment linking /
on “Ownership of AI-Generated Code Hotly Disputed”Submitted Claude.md: Best Practices for Optimizing with Prompt Learning as a story · 3 points
HN discussionHow do you compare to a platform like Arize? https://arize.com/
Comment linking /
on “Launch HN: UpTrain (YC W23) – Open-source performance monitoring for ML models”Submitted Explainability in Machine Learning: Top Techniques as a story · 3 points
HN discussionWe (Dylan, Alex, Adam) built this to answer “what actually happened?” in Claude Code runs to debug things like nested tool calls, prompt bloat, token/cost spikes... It’s an open proxy on LiteLLM that emits OTEL + OpenInference spans to Arize-Phoenix.Giving you access to Full traces with internal prompt content, tool calls, streaming chunks, costs, and latency. No signup; works with the Claude Code CLI unchanged; MIT…
Comment linking /blog/claude-code-observability-and-tracing-introducing-dev-agent-lens/
on “Claude Code Observability via LiteLLM and OpenInference”Submitted What agent traces can tell you without an LLM judge as a story · 2 points
HN discussionThat looks great! Any plans on allowing exports to OpenTelemetry apps like Arize Phoenix? I am looking for ways to connect my Claude Code using Max plan (no API) to it and the best I found was https://arize.com/blog/claude-code-observability-and-tracing... , but it seems kinda overweight.
Comment linking /blog/claude-code-observability-and-tracing-introducing-dev-agent-lens/
on “A MitM proxy to see what your LLM tools are sending”Submitted Auto optimization of Claude.md with prompt learning as a story · 2 points
HN discussionSubmitted LLM Evaluation: Everything You Need to Run, Benchmark Evals as a story · 2 points
HN discussionSubmitted Agent harnesses have an expiration date as a story · 1 points
HN discussionSubmitted Code is free, technical debt isn't: Notes from AI Engineer Europe as a story · 1 points
HN discussionSubmitted The Rise of the ML Engineer as a story · 1 points
HN discussion
