Results
7 articlesSort
1:06:15EN
Cognitive Revolution "How AI Changes Everything"· Sep 14, 2024PodcastJailbreaks Got Harder. Scale Made One Attack Worse.Host Nathan LabenzHaize Labs spent a month automatically attacking OpenAI's o1. The model reasons more carefully about what it should refuse — except when you teach it a homemade cipher.
3:53:04ENCognitive Revolution "How AI Changes Everything"· Dec 27, 2023PodcastHe Red-Teamed GPT-4 and Got Cut Off. The Control Gap Is Still OpeningHost Nathan LabenzNathan Labenz tells Rob Wiblin how an early look at GPT-4, a thin red-team program, and a year of OpenAI's public safety moves reshaped his view of the AGI race.
1:23:53ENCognitive Revolution "How AI Changes Everything"· Mar 17, 2023PodcastGPT-4, 24 Hours Later: No Safety Locks, a Captcha Hire, and a U.S.–China DeadlockHost Nathan LabenzA day after OpenAI shipped GPT-4, ChinaTalk sat a red teamer, a pessimist, and a policy researcher down to argue over capability, safety, and a race nobody can brake.
1:56:35ENCognitive Revolution "How AI Changes Everything"PodcastFrom Autocomplete to Alien Optimizer: Riley Goodside on Three Eras of PromptingHost Nathan LabenzScale AI's first staff prompt engineer traces how language models went from pure text prediction to instruction following to RLHF, and what that means for building with them.
1:22:57ENCognitive Revolution "How AI Changes Everything"PodcastHuman-Level but Not Human-Like: A GPT-4 Red Teamer on What He Saw Behind the MaskHost Nathan LabenzNathan Labenz recounts two months of full-time testing of an early GPT-4, from the AI doctor of his dreams to a model that would plan assassinations on request.
1:37:47EN
Lenny's PodcastPodcast · 2 speakersYou Can Patch a Bug, but You Can't Patch a Brain: Why AI Guardrails FailGuest Sander Schulhoff · Host Lenny RachitskyAdversarial-robustness researcher Sander Schulhoff explains why prompt injection and jailbreaks remain unsolved, why guardrail products don't deliver, and what teams can do instead.
1:32:41ENLenny's PodcastPodcastYou Can Patch a Bug but You Can't Patch a Brain: Why AI Guardrails FailHost Lenny RachitskyHackAPrompt's Sander Schulhoff explains why prompt injection and jailbreaking remain unsolved, why the guardrail industry is selling false comfort, and what organizations can do instead.