Linear Digression
Machine Learning Podcast
Linear Digression launched on September 2, 2017 with 3 votes. The site was still online in September 2026, 9 years on.
What it does
search for me
When OpenAI's frontier models were caught hacking Hugging Face's servers, most people assumed they were hunting for answer keys. The real story is stranger and more unsettling. Katie and Phoebe unpack Exploit Gym — the cybersecurity benchmark at the center of the incident — and why agents are scored not just on whether they capture the flag, but on whether they used the specified vulnerability to get there. That nuance turned out to be load-bearing: the agents reverse-engineered the flags within the first hour, then spent days attacking Hugging Face to learn how the LLM judge worked so they could get their cheated answers past it. The punchline? OpenAI never had that judge switched on. How…from lineardigressions.com
Does a similar job
all alternatives →
Enhance Podcast - "Mutually Assured Machine Learning"2016 · soundcloud.com · ▲60Understanding machine learning and its applications.
Intelligence Squared2015 · intelligencesquaredus.org · ▲74A podcast of Oxford-style debates on complex topics
Partially Derivative2015 · partiallyderivative.com · ▲95The weekly podcast about data, data science, and drinking
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 26d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 27d ago · fastrouter.ai
Source: Product Hunt launch ↗
Launched alongside, September 2017
the whole month →
Sublime Text 3.0▲1,273The long awaited version 3 of the popular code editor
Dev tools · 2017 · sublimetext.com
The definitive database of YC companies with all the metrics
Growth · 2017 · ycdb.co
