Top all-time · #10003
TensorZero Blog
Company blog · tensorzero.com/blogaiprogramming
TensorZero Blog is the company blog at tensorzero.com, writing about ai and programming. Since 2024, 7 different Hacker News readers have linked it 23 times, most often “We raised $7.3M to build an open-source stack for industrial-grade LLM apps”. It is still writing: the last post was on 2026-05-12, and you can follow it by feed.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
HN commenters link TensorZero's posts as related work on fine-tuning small models from curated large-model outputs, and on the project's funding and maintenance status. The comments do not judge the writing.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
TensorZero builds open-source tools for production-grade LLM applications: LLM gateway, observability, optimization, evaluations, and experimentation.
Most-linked posts?
- We raised $7.3M to build an open-source stack for industrial-grade LLM apps2 people · 2 mentions · first linked 2025-08-19
What Hacker News says?
TensorZero | https://github.com/tensorzero/tensorzero | Founding Member of Technical Staff | NYC (onsite) | Full-time TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models. We're looking for a Founding Member of Technical Staff with any of the following skillsets: ‣ Back-end / Systems Engineering (Rust) ‣ Front-end / Design Engineering (…
Comment linking /jobs
on “Ask HN: Who is hiring? (April 2025)”Submitted Reverse Engineering Cursor's LLM Client as a story · 159 points
HN discussionTensorZero | https://github.com/tensorzero/tensorzero | Founding Member of Technical Staff | NYC (onsite) | Full-time TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation. Open Roles: ‣ Back-end Engineering (Rust) ‣ Design Engineering ‣ Developer Relations (DevRel) Engineering ‣ Front-end Engineering (React)…
Comment linking /jobs
on “Ask HN: Who is hiring? (July 2025)”Submitted Fine-tuned small LLMs can beat large ones with programmatic data curation as a story · 53 points
HN discussionThis is neat! I think in general there are really deep connections between semantically meaningful diffs (across modalities) and supervision of AI models. You might imagine a human-in-the-loop workflow where the human makes edits to a particular generation and then those edits are used as supervision for a future implementation of that thing. We did some related work here: https://www.tensorzero.com/blog/automatical…
Comment linking /blog/automatically-evaluating-ai-coding-assistants-with-each-git-commit/
on “Diffsitter – A Tree-sitter based AST difftool to get meaningful semantic diffs”Submitted Is OpenAI's Reinforcement Fine-Tuning (RFT) Worth It? as a story · 4 points
HN discussionWe recently ran similar experiments and saw that fine-tuning small models on automatically curated high-quality outputs from a large model can beat large-model performance while reducing inference costs by up to 30x and inference time by up to 4x. We benchmarked closed-source (OpenAI, Google) and open-source (Qwen) models on multi-turn maze navigation (BabyAI), agentic RAG (Multi-Hop), and agentic tool use (τ-bench)…
Comment linking /blog/curated-behavior-cloning-small-llms-can-beat-large-ones-at-5-30x-lower-cost/
on “Supervised fine tuning on curated data is reinforcement learning”Submitted Bandits in Your LLM Gateway as a story · 3 points
HN discussionhttps://www.tensorzero.com/docs/gateway/benchmarks :)
Comment linking /docs/gateway/benchmarks
on “Show HN: TensorZero – open-source data and learning flywheel for LLMs”Submitted 'Distealed' LLMs: smarter, 5-30x cheaper inference as a story · 3 points
HN discussionhttps://www.tensorzero.com/docs has similar abstractions but doesn't require Python and doesn't require committing to the framework or a language. It's also pretty hard to onboard, but solves the same problems better and makes evaluating changes to models / prompts much easier to reason about.
Comment linking /docs
on “If Dspy is so great, why isn't anyone using it?”Submitted Automatically Evaluating AI Coding Assistants with Each Git Commit as a story · 3 points
HN discussionSeed was in Aug ‘25 and website simply says the project will no longer be maintained: https://www.tensorzero.com/
Comment linking /
on “AI OSS tool repo goes archived over night after raising $7.3M Seed”Submitted Even (very) noisy LLM evaluators are useful for improving AI agents as a story · 2 points
HN discussionThe title makes it sound like they just did a seed round, but the seed round was announced in August of last year [0]. Their website landing page is now also showing the software is no longer maintained. No mention of why they made this decision, my best guess is they burned through their seed money and were unable to attract further investments. [0]: https://www.tensorzero.com/blog/tensorzero-raises-7-3m-seed-...
Comment linking /blog/tensorzero-raises-7-3m-seed-round-to-build-an-open-source-stack-for-industrial-grade-llm-applications/
on “AI OSS tool repo goes archived over night after raising $7.3M Seed”Submitted We're building an automated AI engineer, and it works as a story · 2 points
HN discussionSubmitted Think of LLM Applications as POMDPs – Not Agents as a story · 2 points
HN discussionSubmitted Stop comparing price per million tokens: the hidden LLM API costs as a story · 1 points
HN discussionSubmitted We raised $7.3M to build an open-source stack for industrial-grade LLM apps as a story · 1 points
HN discussionSubmitted From NER to Agents: Does Automated Prompt Engineering Scale to Complex Tasks? as a story · 1 points
HN discussionSubmitted Case Study: Automating Code Changelogs at a Large Bank with LLMs as a story · 1 points
HN discussion