Pedro Domingos: Recurrence Over Input Sequences Is Bad, Recurrence in Inference Depth Is Good
pmddomingos · x · 2026-09-07
AI researcher Pedro Domingos distills his architecture take into two lines: recurrence in the input sequence is bad, recurrence in inference depth is good—i.e., avoid RNN-style stepwise loops and instead deepen computation by iterating within a single inference pass, echoing the recent success of thinking and iterative reasoning.
More from Research
- DEX-Comp Compresses RAG Context 16x While Matching or Beating Uncompressed Baselines — _reachsumit · 2026-09-07
- APT-RAG Builds Adaptive Reasoning Trees for QA Over Hundreds of Documents — _reachsumit · 2026-09-07
- Allegro details AlleCompanion: category-constrained two-tower model for complementary recommendations — _reachsumit · 2026-09-07
- LLMs aren't creating a new intellectual program — they're reviving symbolic AI's old questions — Amichayg · 2026-09-07
- Embedding Surgery: query-time localized vector edits fix dense retrieval rankings, +60% nDCG@10 — _reachsumit · 2026-09-07
- Paper: knowledge-graph memory with forgetting beats flat vector retrieval for agents — burkov · 2026-09-07