Chaînes mises à jour récemment

Choisissez-en une pour ne voir qu’elleToutes les chaînes →

Résultats

98 articles
Trier
8 diapositives18:27EN
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.Code review & verificationAgents de codeWorkflows de développement et tests+2
8 diapositives15:27EN
AI Engineer· 25 oct. 2026What AI Engineers Do Now: Build the Loop Around AgentsAparna Dhinakaran · Arize AIAparna Dhinakaran argues that AI engineers are moving from shipping individual features to building systems that let agent teams improve them. At Arize, that means tracing agent behavior, evaluating its work against human judgment, and feeding those signals back into an always-on agent.Ingénierie d’agentsÉvaluationsObservabilité et fiabilité+2
5 diapositives34:11EN
GOTO Conferences· 23 oct. 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.Workflows de développement et testsCode review & verificationObservabilité et fiabilité+2
3 diapositives13:21EN
Adrian Twarog· 21 oct. 2026Adrian Twarog: Giving Enterprise Vibe Coding a Governed Path to ProductionAdrian TwarogA Superblocks walkthrough shows how shared integrations, isolated databases, policy agents and audit logs can bring business-built AI apps under IT oversight.Vibe CodingIA en entrepriseAI security+2
1:26:46EN
Cognitive Revolution "How AI Changes Everything"· 8 oct. 2026PodcastThere Likely Is a Level of Intelligence We Shouldn't Go PastAnime : Nathan LabenzNathan Labenz brings notes from The Curve, a chip startup whose token bill beat payroll, and a software industry that now performance-reviews people for Claude slop.Entreprise et stratégieSécurité et gouvernanceAGI Timelines+3
1:10:12EN
Cognitive Revolution "How AI Changes Everything"· 7 oct. 2026PodcastOutSystems Went From 4 Major Features a Quarter to 26. Token Spend Fell AnywayAnime : Nathan LabenzCEO Woodson Martin on software that never breaks, why most enterprise work does not need a frontier model, and how AI is finally shrinking the IT backlog.Entreprise et stratégieIA en entrepriseAgents de code+3
13:12EN
OpenAI· 7 oct. 2026Alexandra Lato on Building Stack Overflow for Agents and Stack Internal with CodexAarti Bagul, Alexandra Lato · OpenAIStack Overflow’s VP of Product explains how a small team used Codex with opposite constraints on two products—and why agent-native design means letting agents contribute knowledge, not just read it.Agents de codeIA en entrepriseAgents+2
38 diapositives1:01:33EN
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.Agents de codeAgent skillsWorkflows de développement et tests+2
2:10:42EN
Cognitive Revolution "How AI Changes Everything"· 28 août 2026PodcastThe Exam Papers Nobody AuditsAnime : Nathan LabenzFrontier labs buy reinforcement-learning environments from a cottage industry of small vendors, and almost nobody checks whether those tests match the real work.Évaluations et observabilitéÉvaluationsReward hacking+3
5:15:51EN
Lex Fridman· 26 août 2026Podcast · 2 voixDHH Did Not Write a Line of Omarchy QuattroInvité : DHH · Anime : Lex FridmanThirteen months after a skeptical conversation with Lex Fridman, the Rails creator describes how Opus 4.5, a swarm of coding agents, and a one-minute Linux installer ended his era of hand-chiseled Ruby.Agents de codeVibe CodingIngénierie d’agents+3
1:04:14EN
Unsupervised Learning: With Jacob Effron· 31 juil. 2026PodcastThe Man Who Helped Stand Up Colossus in 120 Days Is Betting on an AI That Lives in Your HouseAnime : Jacob EffronxAI co-founder Igor Babuschkin left to start River AI, arguing coding agents have crossed a threshold, closed labs are getting squeezed, and the next prize is personal, local intelligence.AgentsAI startups & small teamsCompany Building+3
51:31EN
Sequoia Capital· 21 juil. 2026PodcastThey Refunded Nearly $2 Million. Then Factory’s CEO Explained the Dark FactoryMatan Grinberg on being two years early, why a model-agnostic harness beats lab co-design, and why 90 percent of coding tokens will soon run with the lights off.Agents de codeHarness engineeringModel routing & gateways+3
51:09EN
Sequoia Capital· 11 juin 2026PodcastBuild like the model will eat your harness in a yearLogan Kilpatrick, who leads Google AI Studio and the Gemini API, tells Sequoia's Sonya Huang why agent scaffolding is a 12-month asset, why coding already feels like narrow superintelligence, and why Google is optimizing for outcomes instead of eyeballs.AgentsIngénierie d’agentsHarness engineering+3
1:13:33EN
Unsupervised Learning: With Jacob Effron· 3 juin 2026PodcastA Trillion Tokens Later, the Concept Finally Lands: Łukasz Kaiser on What Transformers Still MissAnime : Jacob EffronThe Attention Is All You Need co-author tells Unsupervised Learning that transformers will probably keep winning — and that they still do not learn the way people do.Modèles et entraînementAI researchAgents de code+3
41:09EN
No Priors: AI, Machine Learning, Tech, & Startups· 28 mai 2026Podcast · 2 voixAfter Agents Leak Tokens and Wipe Databases, Onyx Trains Small Models to Watch the Big OnesAnime : Sarah Guo, Elad GilTwo years ago enterprise security buyers told Maxim Bar Kogan he was too early. Now Fortune 10 companies are calling a sub-100-person Israeli startup because they cannot stop agent adoption — only reduce the chance the next action is illegitimate.SécuritéAI securityIngénierie d’agents+3
45:33EN
Sequoia Capital· 26 mai 2026PodcastCursor Ships 1TB of Composer Weights Across Oceans in Under a MinuteFederico Cassano and Fireworks' Dima walk through the globally split RL stack that trained Composer 2 on a sparse trillion-parameter MoE.Infrastructure et déploiementDistributed training & inferenceReinforcement Learning+3
2:12:51EN
Cognitive Revolution "How AI Changes Everything"· 19 avr. 2026PodcastSteve Newman’s fifteen-app stack exists so he only has to look at one screenAnime : Nathan LabenzThe Writely founder walks Nathan Labenz through a vibe-coded attention firewall, a conservative security stance, and why astonishing models still leave him far from AGI.Agents de codePersonal agentsWorkflow automation+3
1:06:31EN
No Priors: AI, Machine Learning, Tech, & Startups· 20 mars 2026Podcast · 2 voixAndrej Karpathy Hasn't Typed a Line of Code Since DecemberAnime : Sarah Guo, Elad GilOn No Priors, the OpenAI cofounder and former Tesla AI director describes the loopy era of coding agents, AutoResearch, and why the bottleneck is now the human.Agents de codeAutoresearchAgent orchestration+3
54:26EN
Cognitive Revolution "How AI Changes Everything"· 22 févr. 2026PodcastTen Billion Active Parameters, and the Unsexy Work of Making Them Agent-ReadyAnime : Nathan LabenzMiniMax researcher Olive Song explains how M2 was trained with expert developers as reward models, interleaved thinking, and a perturbation pipeline that treats every scaffold change as the real generalization test.Agents de codeReinforcement LearningIngénierie d’agents+3
1:57:56EN
Cognitive Revolution "How AI Changes Everything"· 5 févr. 2026PodcastA Hundred Million Lines at Twenty Cents Each: Inside Blitzy's Enterprise Coding PipelineAnime : Nathan LabenzCEO Brian Elliott and CTO Sid Pardeshi tell Nathan Labenz how Blitzy turns a giant codebase into a map, then lets thousands of dynamically generated agents ship most of a multi-month project in days.Agents de codeAgent orchestrationIngénierie du contexte+3
48:03EN
Sequoia Capital· 27 janv. 2026PodcastCoding Will Be Solved. The Bottleneck Is Saying What You WantWarp founder Zach Lloyd tells Sequoia's Sonya Huang why a rebuilt terminal became the lucky form factor for coding agents, and why he stopped subsidizing tokens.Agents de codeIngénierie d’agentsDeveloper productivity+3
2:12:31EN
Cognitive Revolution "How AI Changes Everything"· 25 janv. 2026PodcastMost Caffeine users have no idea they are on a blockchainAnime : Nathan LabenzDFINITY's Dominic Williams tells Nathan Labenz why a tamper-proof, unstoppable cloud is the right backend for AI that writes software from a chat box.Infrastructure et déploiementAgents de codeSécurité et gouvernance+3
2:29:42EN
Cognitive Revolution "How AI Changes Everything"· 18 janv. 2026PodcastTwelve hooks and thirty files: Daniel Miessler’s personal OS on Claude CodeAnime : Nathan LabenzThe PAI framework treats scaffolding, not the model, as the product — a goal-centered agent stack that Miessler thinks will decide both knowledge-work automation and the next cybersecurity race.Agents de codeIngénierie d’agentsIngénierie du contexte+3
1:54:30EN
Cognitive Revolution "How AI Changes Everything"· 9 janv. 2026PodcastFrom One in Ten Cancer Cells to One in a MillionAnime : Nathan LabenzNathan Labenz's solo AMA updates his son's lymphoma treatment, calls Claude Opus 4.5 software AGI, and ranks the live players of early 2026.Entreprise et stratégieAI StrategyAgents de code+3
Charger plus24 sur 98 affichés