StepFun Open-Sources onPanda, Its Internal LLM Annotation and Debug Tool
- Source
- StepFun
- Date
We’ve open-sourced onPanda 🐼 — the tool we use internally for LLM data annotation and model inspection. The workflow is simple: find an error, correct the token, and let the model continue. ✍️ Data annotation - 52% lower median annotation time vs. manual post-editing - SFT + preference data in one workflow, with high on-policy fidelity (ΔPPL <1% vs. the model’s resampling baseline) - Precise token-level supervision with paired positive/negative examples, plus agent-trajectory annotation across image, audio, and video 🔎 Model inspection and debugging - Inspect token probabilities and top-k alternatives, steer decoding token by token, and explore SVG generation, web development, and agent tasks directly in the browser. Try it (mobile-friendly): https://t.co/57vAeJetWD Paper: https://t.co/1MX1eVTREL
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
onPanda gives teams a free, browser-based way to do -level data annotation and decoding-time debugging, a workflow StepFun says cuts annotation time roughly in half versus manual post-editing.
postStepFun Open-Sources Step Code, a CLI Coding Agent Benchmarked on Terminal-Bench
postStepFun debuts StepAudio 3 voice model family, tops real-time benchmarks- postvLLM gains an experimental Attention-FFN disaggregation plugin for MoE
- postOpenRouter free tier for Step 3.5 Flash jumps to 10K calls a day
Checking sign-in…
Loading comments…