I Built a UI to finetune LLMs x100 faster
After fine-tuning GPT for a personal project, I realized how tedious it is to write plain text in a massive JSON file. That's why I built this app for my own use, and I want to see if others could benefit from a tool like this as well ;)
Does the same job
all alternatives →- ABA Better LLM UI in Emacs2024 · x.com · ▲8
All LLM user interfaces I've seen so far are somewhat frustrating: * ChatGPT web requires a lot of copy-paste, it rewrites whole document even if you need to update a part of it, etc. * Github Copilot completions are rather unreliable and do not leave an option to specify what you want; Copilot's chat sidebar is little more than ChatGPT integrated into the IDE * Google Docs have right UI for non-code text, but they use really dumb model (not Gemini 1.5 Pro). Also won't work for code. So... I wrote a Emacs Lisp function which calls LLM with contents of the buffer to generate text according to…
- PRPrompt-refiner – Lightweight optimization for LLM inputs and RAGDec 2025 · github.com · ▲7
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
- ELExperiment ▴ LLM UI for developers with tool use visualization2025 · github.com · ▲8
Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different: Key Features: - Load and edit chat completion logs from CSV files - Fork and modify specific conversation entries - Run inference via Anthropic, Mistral, and OpenAI - Define custom tools using JSONSchema format - Visual tool usage analysis with collapsible, sorted key-value pairs - Full mobile support and available as installable PWA Technical Highlights: - Built with React using custom isomorphic architecture -…
- NTNabu (TTS Reader and LLM Playground on Android)2025 · github.com · ▲7
With the latest launch from Google I've added support for Gemma 3 270M, the speed for local LLM to TTS token time is incredible! This is an heavy obvious work in progress - any contributions or tips would be welcome. The idea is to have a fast moving edge model playground, and maybe have some utility (like the e reader) on the side.
- IWI wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the browserJul 2026 · aidekin.com · ▲5
- BABuilt a visual UI editor that exports to code2025 · license.builtwithpaper.com · ▲6
I've been specializing in UI for over a decade. Using code for UI is great but I always wished there was a more visual code to build apps and sites. So I went ahead and built it. Decided to build it with Compose Multiplatform since I work a lot with Kotlin. Currently exports to CMP as it was simpler due to the context switch. You can try it for free and export some apps
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, October 2024
the whole month →


Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io

One inbox for all your work discussions
Work · 2024 · generalcollaboration.com