Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// ∞ Reasoning & Test-Time Compute

Self-Consistency

Samples many reasoning paths and takes the majority answer.

自洽性投票 2022 Foundational core

Original paper ↓ What to learn first →

IN PLAIN WORDS

Sample many CoT answers at higher temperature; answers reached by diverse paths are likelier correct. The simplest form of test-time scaling.

Used in: maj@k / cons@64 in reasoning evals

TIMELINE · prerequisites → this → what builds on it

2022 Chain-of-Thou…2022 Self-Consistency2024 Test-Time Com…

01Original paper

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Xuezhi Wang, Jason Wei, Dale Schuurmans, et al. · 2022

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Self-Consistency

Then you can learn

Chain-of-Though…Test-Time Compu… Self-Consistency

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Explainers

04Where the course teaches it

U01 Prompting & Using AI Well Prompting techniques: role, context, examples, step-by-step thinking and structured output. 3 h3 algorithms1 paperslesson ready U52 Reasoning Models: RLVR, GRPO & Test-Time Compute Chain of thought, self-consistency, process rewards, GRPO/DAPO, verifiable rewards and the R1 recipe. 12 h12 algorithms5 papers

On learning paths:Post-training & Reasoning Models

For AI / data

Data updated: AI algorithms & curriculum(UTC+8)