ArbitrAI
Stop overpaying for OCR. Audit 15+ LLMs on your own docs.
What it does
Stop overpaying for LLM calls by defaulting to flagship models. We ran 7,560 tests across 18 models (OpenAI, Anthropic, Google, Mistral) and found that mid-tier models often match state-of-the-art accuracy at 1/10th the cost. Arbitr lets you audit your own documents against 18+ LLMs side-by-side. Compare accuracy, cost, and reliability in real-time to find your perfect model fit. - Side-by-side OCR audit - Cost-per-success metrics - Open-source benchmark framework
Does the same job
all alternatives →- LALLM-aided OCR – Correcting Tesseract OCR errors with LLMs2024 · github.com · ▲479
Almost exactly 1 year ago, I submitted something to HN about using Llama2 (which had just come out) to improve the output of Tesseract OCR by correcting obvious OCR errors [0]. That was exciting at the time because OpenAI's API calls were still quite expensive for GPT4, and the cost of running it on a book-length PDF would just be prohibitive. In contrast, you could run Llama2 locally on a machine with just a CPU, and it would be extremely slow, but "free" if you had a spare machine lying around. Well, it's amazing how things have changed since then. Not only have models gotten a lot better,…
- Q2Qwen-2.5-32B is now the best open source OCR model2025 · github.com · ▲211
Last week was big for open source LLMs. We got: - Qwen 2.5 VL (72b and 32b) - Gemma-3 (27b) - DeepSeek-v3-0324 And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new models. We evaluated 1,000 documents for JSON extraction accuracy. Major takeaways: - Qwen 2.5 VL (72b and 32b) are by far the most impressive. Both landed right around 75% accuracy (equivalent to GPT-4o’s performance). Qwen 72b was only 0.4% above 32b. Within the margin of error. - Both Qwen models passed mistral-ocr (72.2%), which is specifically trained for OCR. - Gemma-3…
- OOOpenLLMetry – OpenTelemetry-based observability for LLMs2023 · github.com · ▲154
Hey HN, Nir, Gal and Tomer here. We’re open-sourcing a set of extensions we’ve built on top of OpenTelemetry that provide visibility into LLM applications - whether it be prompts, vector DBs and more. Here’s the repo: https://github.com/traceloop/openllmetry. There’s already a decent number of tools for LLM observability, some open-source and some not. But what we found was missing for all of them is that they were closed-protocol by design, vendor-locking you to use their observability platform or their proprietary framework for running your LLMs. It’s still early in the…
- APA private, flat monthly subscription for open-source LLMs2025 · synthetic.new · ▲31
Hey HN! We've run our privacy-focused open-source inference company for a while now, and we're launching a flat monthly subscription similar to Anthropic's. It should work with Cline, Roo, KiloCode, Aider, etc — any OpenAI-compatible API client should do. The rate limits at every tier are higher than the Claude rate limits, so even if you prefer using Claude it can be a helpful backup for when you're rate limited, for a pretty low price. Let me know if you have any feedback!
- OSOpen-source model and scorecard for measuring hallucinations in LLMs2023 · vectara.com · ▲65
Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app