Ergebnisse
31 ArtikelSortieren
18:27EN
AI Engineer· 26. Okt. 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.
34:11EN
GOTO Conferences· 23. Okt. 2026Anatoliy Bilenko and Alberto Carretero: Making Database Protocols Reliable with Formal Methods and AIAnatoliy Bilenko, Alberto Carretero · CanonicalCanonical’s database engineers connect executable specifications, model-based tests, failure exploration, and reconstructed execution histories—and explain why none of these techniques proves a real system correct on its own.
1:01:33EN
DeepLearningAI· 22. Sept. 2026Spec-Driven Development with Coding Agents: Write the Spec, Let the Agent BuildAndrew Ng, Paul Everitt · DeepLearning.AIJetBrains developer advocate Paul Everitt walks through a full spec-driven workflow: a project constitution, feature loops of plan–implement–validate, and agent skills that travel across tools. The alternative to vibe coding is a markdown contract the agent cannot forget.
40:13EN
Sequoia Capital· 2. Dez. 2025PodcastAs long as humans still need to read code, the IDE is not dyingZed founder Nathan Sobo argues that source code is a language for people, that terminal agents still need a visual editor, and that conversations should be anchored to every edit.
27:19EN
No Priors: AI, Machine Learning, Tech, & Startups· 23. Okt. 2025Podcast · 2 StimmenThe Turing Test Passed. Warp's CEO Says Nobody Seemed to CareModeration: Sarah Guo, Elad GilZach Lloyd on distilling intelligence without consciousness, why a 40-year-old terminal is the front door for coding agents, and why senior engineers just got more expensive.
37:45ENSequoia Capital· 10. Juni 2025PodcastCodex Is a Thought Experiment: What If the Agent Worked on Its Own Computer?OpenAI’s Codex team on training o3 to write mergeable PRs, running four copies of a 1 a.m. bug, and why the product only clicks once you stop pairing and start delegating.
5:20:08EN
Lex Fridman· 22. März 2025Podcast · 2 StimmenThePrimeagen Would Rather Redesign the Room Than Trust WillpowerGast: ThePrimeagen · Moderation: Lex FridmanLex Fridman talks with Michael Paulson about linked lists, Netflix, Neovim, ADHD, addiction, AI, and the night he says God gave him a conscience.
50:35ENNo Priors: AI, Machine Learning, Tech, & Startups· 13. März 2025Podcast · 2 StimmenCopilot Already Writes Half the Code. GitHub's CEO Says Agents Still Have Four Gates to ClearModeration: Sarah Guo, Elad GilThomas Dohmke on agent mode, why median developers are not going anywhere, and how AI is repricing the tools that write software.
54:47ENSequoia Capital· 4. Feb. 2025PodcastNinety Thousand Games a Day: Roblox's Bet That AI Should Wash the DishesStef Corazza, head of generative AI at Roblox, tells Sequoia how a free Studio assistant, a community data bargain, and a 3D foundation model are meant to teach AI game development.
38:28ENNo Priors: AI, Machine Learning, Tech, & Startups· 8. Okt. 2024Podcast · 2 StimmenHalf of Production AI Is RAG. Fine-Tuning Almost Disappeared.Moderation: Sarah Guo, Elad GilBraintrust CEO Ankur Goyal tells No Priors what Notion, Zapier, and Vercel actually ship — and which hyped techniques they quietly dropped.
53:51ENLiora Friedberg on Solving Puzzles in ProductionYaron Minsky, Liora Friedberg · Jane StreetProduction engineering combines live incident response with software, process improvements and a culture that helps people learn from mistakes. Liora Friedberg and Ron Minsky explore the work at Jane Street.
2:29:04ENLex Fridman· 6. Okt. 2024Podcast · 2 StimmenKeep the Programmer in the Driver's Seat: Cursor's Founders on Tab, Agents, and Zero-Entropy EditingGast: Cursor Team · Moderation: Lex FridmanMichael Truell, Aman Sanger, Sualeh Asif, and Arvid Lunnemark tell Lex Fridman why they forked VS Code, how Tab and Apply actually work, and why most programming still needs a human iterating in real time.
59:11ENSequoia Capital· 25. Juni 2024PodcastDon't Train a Model. Factory's Founders Say Go Dig for GoldMatan Grinberg and Eno Reyes tell Sequoia's Training Data why they sell a fleet of job-specific droids on top of other people's models — and how that stack just took SWE-bench from 14% to 19%.
1:25:10EN
Cognitive Revolution "How AI Changes Everything"· 12. März 2024PodcastWriting Code Is Only 30% of the Job. CodiumAI Wants the Other 70%Moderation: 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.
1:15:39ENCognitive Revolution "How AI Changes Everything"· 29. Nov. 2023PodcastAfter 20 Years of Frontend, v0 Wrote Better Code Than Guillermo Rauch DidModeration: Nathan LabenzThe Vercel CEO tells Nathan Labenz why every product needs ghost text, why Software 2.0 will ossify the old stack, and why betting against open source is still the expensive mistake.
1:32:41ENCognitive Revolution "How AI Changes Everything"· 5. Okt. 2023PodcastThere are maybe 5,000 people who can train frontier models. The rest need AI engineersModeration: Nathan LabenzSwyx of Latent Space tells Nathan Labenz how a new job is forming, why OpenAI will Sherlock its developers, and what still does not count as an agent.
38:13ENNo Priors: AI, Machine Learning, Tech, & Startups· 31. Aug. 2023Podcast · 2 StimmenChatGPT Runs on His Framework. He Still Doesn't Want You Training a ModelModeration: Sarah Guo, Elad GilVercel founder Guillermo Rauch tells No Priors why frontend is the last mile of AI, why first-generation AI frameworks will be rewritten, and why bots are already stealing your tokens.
43:45ENNo Priors: AI, Machine Learning, Tech, & Startups· 3. Aug. 2023Podcast · 2 StimmenEight Years of No Growth, Then OpenAI and NVIDIA Became His CustomersModeration: Sarah Guo, Elad GilWeights & Biases CEO Lukas Biewald tells No Priors how a labeling company with no chasm to cross funded the ML developer tools that trained most of the large language models.
1:23:49ENSteve Lee on PowerShell 7: Compatibility, New Features and the RoadmapSteve Lee · MicrosoftA historical look at the move from Windows PowerShell to cross-platform PowerShell, including demonstrations of the version 7 preview and its compatibility trade-offs.
1:08:43ENRon Minsky on Types and Why They Matter in SoftwareYaron Minsky · Jane StreetType systems can make programs faster, catch mistakes and guide large refactorings, but their value depends on the language and the work. Ron Minsky explains the trade-offs through practical examples.
52:51ENCaveat Configurator: When Configuration Becomes CodeDominick LoBraico · Jane StreetDominick LoBraico explains why flexible OCaml plugins created production problems at Jane Street, and how configuration generation and disciplined plugin management address them.
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.
50:03EN
Lenny's PodcastPodcastCopilot Is a Copilot, Not a Pilot: Inbal Shani on the Future of AI in Software DevelopmentModeration: Lenny RachitskyGitHub's chief product officer explains what AI changes for developers, what it does not replace, and how teams should adopt it.
1:21:34ENLenny's PodcastPodcastGitLab’s Public-by-Default Playbook: Short Toes, Clear Outcomes, and a Platform Built to ShipModeration: Lenny RachitskyDavid DeSanto explains how GitLab turns radical transparency, remote-first operations, and breadth-then-depth product strategy into a faster DevSecOps platform.Mehr laden24 von 31 angezeigt