Recurrent Neural Networks

also referred to as: rnn · rnns

5 statements across 3 episodes · 1 bullish · 1 bearish · 3 people on the record · first statement Jul 21, 2017 by Doug Eck · across every show →

Everything said about Recurrent Neural Networks, oldest first

Jul 21, 2017 negative

Opinion

Eck: Google Magenta's early music generation models were primitive RNNs

“We put out some models that were, you know, by any reasonable account primitive, I mean, kind of very simple recurrent neural networks that that generate MIDI from MIDI”

Doug Eck Jul 21, 2017 ▶ 3:54 Making Music and Art Through Machine Learning - Doug Eck of Magenta · Y Combinator

Jul 21, 2017 neutral

Assertion Supported

Eck: Google AI Duet relies on simple 2002 RNN technology

“And what I noticed, even with AI Duet, which is this like web-based, like, it's a simple RNN. It's like, I can lay claim. It's technology that was published in 2002. It's really a very simple, really simple.”

Doug Eck Jul 21, 2017 ▶ 13:16 Making Music and Art Through Machine Learning - Doug Eck of Magenta · Y Combinator

Nov 8, 2017 bullish

Opinion

Sidor: Rigorous baseline optimization will advance AI more than complex architectures

“And you know, it's not the kind of sexy research that people want to see, where you have like some hierarchy of big RNN, but it actually, this kind of research, I think at this point will advance field the most.”

Szymon Sidor Nov 8, 2017 ▶ 2:33 Building Dota Bots That Beat Pros - OpenAI's Greg Brockman, Szymon Sidor, and Sam Altman · Y Combinator

May 1, 2026 neutral

Opinion

Chaubard: Hierarchical Reasoning Models Offer Little Novelty Over Standard RNNs

“The, this is directly in the lineage of RNNs. There's not that much novel from, like, the RNN standpoint at least in my opinion.”

Francois Chaubard May 1, 2026 ▶ 7:45 Recursion Is The Next Scaling Law In AI · Y Combinator

May 1, 2026 neutral

Insight

Chaubard: Standard LLMs sacrifice latent time compression unlike RNNs

“What you actually paid for that you have to give up is this latent reasoning thing and this compression in the time direction. There is no compression in LMs. Every single decode that I do, I still have to retain the entire, you know, Shakespeare novel just to…”

Francois Chaubard May 1, 2026 ▶ 3:23 Recursion Is The Next Scaling Law In AI · Y Combinator

Recurrent Neural Networks

Everything said about Recurrent Neural Networks, oldest first

Turn any episode into a week of clips.