“GPT 5.6 scores X out of the box and then stays flat… GPT 6 scores much higher… still out of the box and stays flat”

Greg Burnham, or his team at Epoch · The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) · From Math Olympiads to Navier-Stokes: How Fast Is AI Progressing? with Greg Burnham

Play from 52:31
52:31

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

Created a board-game learning benchmark where the same AI instance plays the game repeatedly, takes notes, and is evaluated on improvement across generations (GPT-5.6 vs GPT-6)

Said nearby on the same subject

“A phone with a cord… you pick it up… Popsicle Hotline… free… white-glove service… free candy… board game menu… laundry same day…”
♫
Said on Tony Robbins Podcast Daily
Growth tactic Share this moment
“We build evaluation tools that take expert data sets, expert rubrics, and translate them into a tool that you can actually run to help score what AI is generating”
♫
Said on This Week with EdSurge
“I joined them in playing the game... I became like a baby again, having that with them. It made me realize there is no way they will play this game without shouting.”
OO
Opayemi Ogimadeko
The Voice of Early Childhood ·
How they work Share this moment
“Set up Rate My Clinic where people can get assessments done, find out how they compare on each of those different benchmarks. And importantly, recommendations on how to improve”
♫
Said on The Business of Allied Health
Business model Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.