scikit-learn scikit-learn.org ↗
A Python machine learning library including probability calibration tools.
LibraryAI & MLmachine-learningpythoncalibration
Recommended in 1 thread
Using LLM for confidence scoring is a bad idearumple.github.io ·
Its calibration module was cited as the established science for turning classifier outputs into probabilities.
Similar tools
- Liquid AI Decision Models ↗AI & ML1 thread
Models from Liquid AI trained specifically to produce decisions with calibrated confidence.
- 1 thread
- 1 thread
- CodeCarbon ↗AI & ML1 thread
An open-source Python library for estimating the carbon emissions of compute workloads.
- 1 thread
- 1 thread
- Artificial Analysis ↗AI & ML0 threads
A site benchmarking and comparing AI models on quality, price and speed.
- pstack unslop skill ↗AI & ML1 thread
A Cursor plugin skill that instructs AI agents to avoid sloppy, formulaic prose.
Also in AI & ML
- 7 threads
- 5 threads
- llama.cpp4 threads
A C/C++ engine for running LLMs locally.
- 3 threads
- DeepSeek2 threads
A family of large language models offered via a low-cost API.
- 2 threads
- 1 thread
- Claude1 thread
Anthropic's AI model and command-line assistant.
- Claude Code gateways ↗1 thread
Documented setup for routing Claude Code through an LLM gateway for centralized control and alternate model providers.
- 1 thread
- 1 thread
- Codex1 thread
OpenAI's coding agent.
Link from a commenter, not checked or endorsed by us: ↗ https://scikit-learn.org/stable/modules/calibration.html