Podcast Episodes

Back to Search
"How AI Is Learning to Think in Secret" by Nicholas Andresen

On Thinkish, Neuralese, and the End of Readable Reasoning

In September 2025, researchers published the internal monologue of OpenAI's GPT-o3 as it d…

8 months, 2 weeks ago

Short Long
View Episode
"On Owning Galaxies" by Simon Lermen

It seems to be a real view held by serious people that your OpenAI shares will soon be tradable for moons and galaxies. This includes eminent thinke…

8 months, 2 weeks ago

Short Long
View Episode
"AI Futures Timelines and Takeoff Model: Dec 2025 Update" by elifland, bhalstead, Alex Kastner, Daniel Kokotajlo

We’ve significantly upgraded our timelines and takeoff models! It predicts when AIs will reach key capability milestones: for example, Automated Cod…

8 months, 2 weeks ago

Short Long
View Episode
"In My Misanthropy Era" by jenn

For the past year I've been sinking into the Great Books via the Penguin Great Ideas series, because I wanted to be conversant in the Great Conversa…

8 months, 2 weeks ago

Short Long
View Episode
"2025 in AI predictions" by jessicata

Past years: 2023 2024

Continuing a yearly tradition, I evaluate AI predictions from past years, and collect a convenience sample of AI predictions m…

8 months, 3 weeks ago

Short Long
View Episode
"Good if make prior after data instead of before" by dynomight

They say you’re supposed to choose your prior in advance. That's why it's called a “prior”. First, you’re supposed to say say how plausible differen…

8 months, 4 weeks ago

Short Long
View Episode
"Measuring no CoT math time horizon (single forward pass)" by ryan_greenblatt

A key risk factor for scheming (and misalignment more generally) is opaque reasoning ability.One proxy for this is how good AIs are at solving math …

8 months, 4 weeks ago

Short Long
View Episode
"Recent LLMs can use filler tokens or problem repeats to improve (no-CoT) math performance" by ryan_greenblatt

Prior results have shown that LLMs released before 2024 can't leverage 'filler tokens'—unrelated tokens prior to the model's final answer—to perform…

9 months ago

Short Long
View Episode
"Turning 20 in the probable pre-apocalypse" by Parv Mahajan

Master version of this on https://parvmahajan.com/2025/12/21/turning-20.html

I turn 20 in January, and the world looks very strange. Probably, thin…

9 months ago

Short Long
View Episode
"Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment" by Cam, Puria Radmard, Kyle O’Brien, David Africa, Samuel Ratnam, andyk

TL;DR

LLMs pretrained on data about misaligned AIs themselves become less aligned. Luckily, pretraining LLMs with synthetic data about good AIs help…

9 months ago

Short Long
View Episode

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us