OM DETTA AVSNITT
On Episode 159 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Melanie Mitchell. Melanie talks about the surprising progress made in AI since the '90s, whether real concepts emerge from data scale alone, whether modern connectionist systems extrapolate or only interpolate, and what humans do differently. We also talk about the complex innards of modern transformer networks, measuring alien intelligences, role playing, sycophancy, and security, and why giving answers is easier than posing interesting questions.
Engelsk
USA
I DETTA AVSNITT
UTSKRIFT 🔗
Are you the producer of this podcast?
Add a podcast transcript
Need Audio-to-Text?
Transcribe with Listen411 in Just 60 Seconds
SÖK TIDIGARE AVSNITT
Sök efter tidigare avsnitt från Silver Bullet Security Podcast.
ANDRA EPISODER I DENNA PODCAST
Welcome back to the Silver Bullet Security Podcast, created and hosted by the Berryville Institute of Machine Learning, where we are defining the future of machine learning security. From 2006-2018, we explored the nascent field of software security through the lens of building security in. &…
On Episode 155 of the Silver Bullet Security Podcast, BIML's Gary McGraw hosts Giovanni Vigna. Giovanni talks about the evolution of software exploit and AI, what has happened in the security field since 2011 (and episode 65), getting inside connectionist networks to see what is actually happ…
On Episode 156 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Phil Venables. Phil talks about the evolution of the CISO role from running an engineering team in the '90s back into running an engineering team in the mid-2020s, Agentic AI and tools using tools, the rise of mach…
On Episode 154 of the Silver Bullet Security Podcast, Gary McGraw hosts Gadi Evron. Gadi talks about the [un]prompted conference and its focus on fundamental aspects of machine learning security. The conversation touches on current approaches to MLsec, the words we use to describe AI security…
On Episode 157 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Tim Schulz. Tim talks about whitebox control and observability in machine learning systems (and especially transformer architectures), the limits of red teaming for securing AI, "neural surgery," Agenti…
Ansvarsfriskrivning: Podcasten och konstverket som är inbäddat på den här sidan är från Gary McGraw, som är dess ägares egendom och inte anslutet till eller godkänt av Listen Notes, Inc.
REDIGERA
Tack för att du hjälper till att hålla databasen över podcaster uppdaterad.
