Anything To JSON – a language model for structured extraction
Hey HN! Erik here from banana.dev We’ve trained a small(ish) language model on structured extraction, and today we’re launching a playground for it at https://anythingtojson.com. Give it a try! This model continues our work on structured generation, following last week’s launch of Fructose[1], a python client for strongly-typed LLM responses. There seem to be two distinct halves of the problem intended to be solved by Fructose and structured generation: 1. the reasoning ability of the model, such as performing chain of thought, creative acts, and natural language tasks. In a way,…
In plain words
Anything To JSON is a language model from banana.dev trained specifically for extracting structured data from text and converting it to JSON format. It uses constrained generation and fine-tuning to reliably pull information from unstructured content without generating reasoning or creative responses. The tool is designed for developers who need to parse text data into consistent JSON structures for downstream applications, with a playground available for testing.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! Erik here from banana.dev We’ve trained a small(ish) language model on structured extraction, and today we’re launching a playground for it at https://anythingtojson.com. Give it a try! This model continues our work on structured generation, following last week’s launch of Fructose[1], a python client for strongly-typed LLM responses. There seem to be two distinct halves of the problem intended to be solved by Fructose and structured generation: 1. the reasoning ability of the model, such as performing chain of thought, creative acts, and natural language tasks. In a way, the “business logic”. 2. the structured json response, to make sure the receiving code doesn't break AnythingToJson is intended to solve the latter. No big-brain work, just find data in text and extract it. Constrained generation at inference time helps keep it on track, and our finetuning has improved the accuracy and consistency of extracted data. There’s much more progress to be made (longer context window, hallucination to squash out, etc), but ship early and fast. [1] https://news.ycombinator.com/item?id=39619053
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 · 26d ago · cactuscompute.com
Launched alongside, March 2024
the whole month →
- 3Y
Life & fun · 2024 · github.com
Microlaunch▲1,116Launch and get feedback on both the idea and product
Dev tools · 2024 · microlaunch.net
