reasoning

4 statements across 4 episodes · 3 bullish · 0 bearish · 4 people on the record · first statement Oct 11, 2024 by Ankur Goyal · across every show →

Everything said about reasoning, oldest first

Oct 11, 2024 positive

Insight

Goyal: Systems betting on intrinsic LLM reasoning improvements are more durable

“If you build your system in a way that Kind of assumes LLMs will get better at reasoning and get better at sort of agentic tasks in the LLM itself. Then I think you will build a more durable system.”

Ankur Goyal Oct 11, 2024 ▶ 1:45:53 Production AI Engineering starts with Evals

Mar 23, 2025 bullish

Insight

Agarwal: Classical RL ideas from games are relevant for LLM agents

“When we are again talking about things like agents and reasoning and whatnot, I think a lot of the things are probably done on a small scale in the RL literature, in games and whatnot, and a lot of those ideas would be relevant again now.”

Rishabh Agarwal Mar 23, 2025 ▶ 46:04 The Magic of LLM Distillation — Rishabh Agarwal, Google DeepMind

Jan 23, 2026 neutral

Insight

Yi Tay: 'Reasoning' Technically Just Means Post-Training RL with Thinking Trajectories

“So I think the actual, like, technical definition of reasoning is making models better with thinking and post-training. Ok? Yeah. So basically, like, RL-ing the model to think better.”

Yi Tay Jan 23, 2026 ▶ 33:24 Captaining IMO Gold, Deep Think, On-Policy RL, Feeling the AGI in Singapore — Yi Tay

Apr 3, 2026 bullish

Opinion

Andreessen: Recursive self-improvement and three other AI breakthroughs are actively working

“So the way I think about it is we've had four fundamental breakthroughs in functionality, LLMs, reasoning agents and then and then now RSI and they're all actually working.”

Marc Andreessen Apr 3, 2026 ▶ 11:33 Marc Andreessen introspects on Death of the Browser, Pi + OpenClaw, and Why "This Time Is Different"

reasoning

Everything said about reasoning, oldest first

Turn any episode into a week of clips.