tszzl: interpretability breakthrough feels like my understanding of neural nets jumped five years
tszzl · x · 2026-10-15
In a follow-up, tszzl says Nick Cammarata's 'Neural Networks Are Already Clean' essay catapulted his understanding of neural networks 'five years into the future,' reviving the joy of studying deep learning: 'neurons are already clean! they form a wonderful alien ontology!'
Related event: Ex-OpenAI Interpretable Lead Claims Neural Networks Are Already Clean(5 posts)→
More from Research
- Doc2Harness: New benchmark finds best coding agent passes only 53% across 329 cases — _akhaliq · 2026-10-16
- Stanford's Fei-Fei Li team open-sources OpenWAM, a unified world-action model framework for robots — jiqizhixin · 2026-10-16
- NVIDIA's TacitVLA: robots reason without reading their own thoughts, 3.4x lower latency — arankomatsuzaki · 2026-10-16
- Cohere Labs world model course session 4: DreamerV1-V4 architectures in one go — Cohere_Labs · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- One tiny word changes the conversation: how LLMs pick up on 'just' — StellaLisy · 2026-10-16