Résultats
7 articlesTrier
1:34:29EN
Cognitive Revolution "How AI Changes Everything"· 18 févr. 2026PodcastThree IMO Golds Missed the Same Problem. Harmonic Wants Math to CompileAnime : Nathan LabenzVlad Tenev and Tudor Achim built Aristotle to emit Lean proofs a kernel can check—and they argue that is how mathematical superintelligence stays trustworthy.
1:41:34ENCognitive Revolution "How AI Changes Everything"· 24 déc. 2025PodcastThey Owned the Camera Partition—and Still Couldn't Crash the HelicopterAnime : Nathan LabenzKathleen Fisher and Byron Cook tell Nathan Labenz how formal methods turn some software bugs into closed cases, from a DARPA helicopter to AWS policies checked a billion times a second.
1:25:10ENCognitive Revolution "How AI Changes Everything"· 12 mars 2024PodcastWriting Code Is Only 30% of the Job. CodiumAI Wants the Other 70%Anime : Nathan LabenzItamar Friedman argues that completion is already a commodity, that code integrity is where AI still lags, and that flow engineering—not fancier prompts—is how GPT-4 doubled its score on coding contests.
1:09:24ENYaron Minsky on Effective ML: Writing OCaml for Code ReadersYaron Minsky · Jane StreetPractical lessons from Jane Street on using types, interfaces and abstraction to keep a large OCaml codebase understandable and correct.
51:35ENYaron Minsky on Effective ML: Interfaces, Invariants and Code ReadersYaron Minsky · Jane StreetIn the first part of a 2011 Harvard lecture, Jane Street’s Yaron Minsky shows how OCaml interfaces and types can make long-lived code easier to understand and change.
1:25:13EN
Lenny's PodcastPodcastCodex Is Not Just a Coding Tool: OpenAI's Plan for an Agent That Behaves Like a TeammateAnime : Lenny RachitskyCodex product lead Alexander Embiricos explains the 20x growth, why every useful agent may need to write code, and why human review speed is the real bottleneck.
1:07:48ENLenny's PodcastPodcastMost Productivity Metrics Are a Lie: Nicole Forsgren on Measuring Developer Experience in the AI EraAnime : Lenny RachitskyThe creator of DORA and SPACE explains why lines of code and old pipeline metrics fall short with AI, and how to start improving developer experience by listening, surveying and tying results to what leaders care about.