Quote 106 · ai notis

Said in a video · quote 10611 Oct 2026

12:47 efficiencies Um, reinforcement learning / 12:50 was / 12:52 a little over 10,000 GB300s for four / 12:54 weeks. So, actually there are more flops / 12:55 spent on reinforcement learning.

Who said it is named in the fact below.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

Where it was said

Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha Laskin
No Priors (YouTube) · 9 Oct 2026 · at 12:47

Watch it at 12:47 archived copy

Checked

Matched word for word against the video's transcript by the notis newsroom on 11 Oct 2026.

The fact it supports: Laskin said: "reinforcement learning was a little over 10,000 GB300s for four weeks" (12:47).

In the story

Reflection AI's Laskin says open models will take most token demand 11 Oct 2026

Cite this quote

Short permanent address

In a sentence

“12:47  efficiencies Um, reinforcement learning / 12:50  was / 12:52  a little over 10,000 GB300s for four / 12:54  weeks. So, actually there are more flops / 12:55  spent on reinforcement learning.” From Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha Laskin (No Priors (YouTube)) at 12:47. Quoted by ai notis. https://ainotis.com/q/106

As a reference (APA style)

(2026, October 9). “12:47  efficiencies Um, reinforcement learning / 12:50  was / 12:52  a little over 10,000 GB300s for four / 12:54  weeks. So, actually there are more flops / 12:55  spent on reinforcement learning.” [Video at 12:47]. https://ainotis.com/q/106

Anyone may quote this address. It does not change; if we correct the story, this page says so.