BestHub
Sign in
Tagged articles

Lean theorem prover

8 articles · Page 1 of 1
Model Perspective
Model Perspective
Oct 22, 2026 · Artificial Intelligence

AI's Best Learning Trick: Designing 15% Failure for Faster Mastery

The article argues that AI's greatest value in learning isn't providing answers but precisely calibrating difficulty to maintain an 85% success rate, citing the '85% rule' from a 2019 Nature Communications paper and detailing six evidence-based techniques like productive failure, teaching virtual students, error detection, confidence-based practice, and interleaved problem sets.

85% ruleAI-assisted learningLean theorem prover
0 likes · 8 min read
AI's Best Learning Trick: Designing 15% Failure for Faster Mastery
Java Architect Essentials
Java Architect Essentials
Oct 19, 2026 · Artificial Intelligence

Claude's Lean Proof Solves Critical Percolation in Dimensions 3–10

Anthropic's Claude helped produce a mechanically verified Lean proof for critical bond percolation on integer lattices across all finite dimensions d≥2, resolving a long-standing conjecture for dimensions 3–10 through human-AI collaboration using formal verification.

AI-assisted mathematicsAnthropic ClaudeHugo Duminil-Copin
0 likes · 7 min read
Claude's Lean Proof Solves Critical Percolation in Dimensions 3–10
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 7, 2026 · Artificial Intelligence

OpenAI Drops 722 Math Papers Overnight: Riemann, BSD, Hodge Conjectures Claimed

OpenAI released 722 mathematical manuscripts from an unreleased internal model, claiming progress on millennium problems like the Riemann hypothesis, BSD conjecture, and Hodge conjecture, but Fields medalists and other mathematicians warn the volume exceeds human verification capacity and do not endorse the results.

AI-generated proofsBSD conjectureFields Medalists
0 likes · 12 min read
OpenAI Drops 722 Math Papers Overnight: Riemann, BSD, Hodge Conjectures Claimed
AI Product Manager Community
AI Product Manager Community
Oct 7, 2026 · Industry Insights

Terence Tao's U-Turn: Why AI Math Benchmarks Risk 'Proof Indigestion'

Fields Medalist Terence Tao, once an AI enthusiast, now warns that AI companies treating mathematics as benchmarks produce proofs without human understanding, causing 'proof indigestion' and eroding the cognitive friction essential for mathematical insight, likening unchecked AI-generated proofs to degenerative cloning.

AI benchmarksAI in mathematicsFields Medalists
0 likes · 9 min read
Terence Tao's U-Turn: Why AI Math Benchmarks Risk 'Proof Indigestion'
Architect
Architect
Sep 18, 2026 · Artificial Intelligence

What Fermat's Last Theorem Formalization Reveals About Multi-Agent Collaboration

Anthropic's 11-day project formalizing Fermat's Last Theorem in Lean with 30,000 machine-checked theorems exposes five critical patterns for multi-agent systems: verifiable artifacts, dynamic task graphs, evidence-based planning, verification-gated state changes, and recoverable execution state.

Fermat's Last TheoremLean theorem proverProve2Me
0 likes · 26 min read
What Fermat's Last Theorem Formalization Reveals About Multi-Agent Collaboration
PaperAgent
PaperAgent
Sep 6, 2026 · Artificial Intelligence

Anthropic's Killer Multi-Agent Blueprint: One Loop, Skills, Harness & Snapshot Eval

Anthropic's production e-commerce and math-formalization agents share a unified architecture: a single-model loop with modular skills, tool calls to existing systems, code-enforced harness rules, and snapshot-based evaluation, enabling scalable, verifiable multi-agent systems.

Agent ArchitectureAnthropicLLM Engineering
0 likes · 17 min read
Anthropic's Killer Multi-Agent Blueprint: One Loop, Skills, Harness & Snapshot Eval
AI Engineering
AI Engineering
Sep 5, 2026 · Artificial Intelligence

Claude Formally Proves Fermat's Last Theorem in 11 Days with 13M Lines of Lean Code

Anthropic's Claude AI completed the first full formal verification of Fermat's Last Theorem in 11 days, generating over 13 million lines of Lean code and 29,500 intermediate theorems using the Prove2Me platform, with independent verification by the nanoda kernel, signaling a shift in mathematical proof validation.

AnthropicClaude AIFermat's Last Theorem
0 likes · 5 min read
Claude Formally Proves Fermat's Last Theorem in 11 Days with 13M Lines of Lean Code