Resultados
6 artículosOrdenar
18:27EN
AI Engineer· 26 oct 2026Daksh Gupta on Building a Better AI Code Review AgentDaksh Gupta · GreptileGreptile co-founder Daksh Gupta explains why a webhook plus a coding agent is not enough for reliable pull-request review—and how targeted prompts, incident data, model inversion, codebase context, browser testing, and task-specific model routing can help.
1:34:29EN
Cognitive Revolution "How AI Changes Everything"· 18 feb 2026PódcastThree IMO Golds Missed the Same Problem. Harmonic Wants Math to CompilePresenta: 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 dic 2025PódcastThey Owned the Camera Partition—and Still Couldn't Crash the HelicopterPresenta: 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 mar 2024PódcastWriting Code Is Only 30% of the Job. CodiumAI Wants the Other 70%Presenta: 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.
1:25:13EN
Lenny's PodcastPódcastCodex Is Not Just a Coding Tool: OpenAI's Plan for an Agent That Behaves Like a TeammatePresenta: 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 PodcastPódcastMost Productivity Metrics Are a Lie: Nicole Forsgren on Measuring Developer Experience in the AI EraPresenta: 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.