“Our model grader identified 10 rollouts, or approximately 1 to 2 rollouts per 1,000, Bayesian mean posterior rate of 0.17%, 95% interval of 0.09% to 0.28%”

LessWrong (Curated & Popular) · "GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman

Play from 21:00
21:00

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

What was described

used a model grader to scan 6,452 GLM-5.3 rollouts for verbalized update-aware reasoning and counted the occurrences

10 rollouts identified, ~0.17% rate (1-2 per 1,000), 95% CI 0.09-0.28%

Said nearby on the same subject

“I have eight different local models, open weight models running right now in my house, in my attic... they all have personas. My most recent is GLM-5.3 persona.”
ST
Spencer Thompson
Intelligent Machines (Audio) ·
Automation 8 models Share this moment
“Monopoly cards… with a QR code that was like buy this property… counting the scans allows them to become trackable.”
KH
Kirby Hasseman
Human-First AI Marketing Podcast by Avenue9 ·
Growth tactic Share this moment
“You can get a lot from looking at a ton of different rollouts and just trying to understand how the model thinks”
EB
Eric Bigelow
"The Cognitive Revolution" ·
How they work Share this moment
“We have a bunch of fine-tuned models ourselves too… making us more innovative… couldn’t do with the frontier models because of cost and efficiency reasons”
♫
Said on All-In with Chamath, Jason, Sacks & Friedberg
Why it worked 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.