WaveNet turns 10: long-context autoregression a year before Transformers existed
teropa · x · 2026-09-09
DeepMind researcher Sander Dieleman marks the 10th anniversary of WaveNet, the landmark 2016 speech and music generation work. He jokes that skipping Transformers looks silly in hindsight, but the architecture simply wouldn't be invented for another year.
Related event: WaveNet Marks 10th Anniversary as Foundational Audio Generation Paradigm(4 posts)→
More from Models
- NVIDIA Ships Qwen 3.8 27B NVFP4 Quantized Model on Hugging Face — TheZachMueller · 2026-09-09
- Hands-on: ChatGPT Images 2.5 shows precise local editing of infographics — xiaohu · 2026-09-09
- Early user: GPT-6 Astra's video understanding identifies everything 'with 100% accuracy' — imjustnewatai · 2026-09-09
- Should AI agents pause to think in game benchmarks? Latency vs. decision-making — imjustnewatai · 2026-09-09
- OpenAI Launches GPT-Image 2.5 With Better Multi-Turn Editing and Reference Preservation — Simon Willison · 2026-09-09
- Is over-RL making models over-literal? A case on 'caveman speak' in CoT — mike64_t · 2026-09-09