Agents still bad at dependent types: their instincts skew imperative even when writing Lean
hargup13 · x · 2026-10-25
A developer observes that AI agents are not yet good at dependent types: even when writing Lean, their instincts pull them too much toward imperative programming, struggling with the dependent-type paradigm. The post highlights a capability gap for coding agents in formal verification and other highly abstract domains.
More from coding & agent
- Live MCP rewrite from Node to Rust cuts memory usage by roughly 8x — draginol · 2026-10-25
- Your notes are untapped agent context: why journaling beats generic prompts — EXM7777 · 2026-10-25
- Dev offers to pay extra for a 'terse mode' that caps agent replies at 5 lines — weswinder · 2026-10-25
- Agent builds 100%-reliable Node.js brotli exploit in 5 unsupervised hours — jcran · 2026-10-25
- Dev builds interactive 3D energy textbook covering full GCSE topic with Opus 5.5 and Three.js — Afinetheorem · 2026-10-25
- Codex CLI 0.164.0 Adds Presets: Save Prompts and Settings, Recall via Ctrl+X P — pvncher · 2026-10-25