YoutuBlog (HackerTube) : lire les conférences et podcasts de YouTube
Derniers articles
6 204 articlesTrier
48:20EN
Theo - t3․gg· 10 nov. 2026Fable 5.2 is powerful, but Theo Browne still prefers Opus for everyday codingTheo Browne · T3After a day of tests, Browne compares benchmarks, usage limits and the mistakes that still require a human reviewer.
43:35EN
Silicon Valley Girl· 10 nov. 2026Isomorphic Labs’ Max Jaderberg on narrowing drug designs with AIInvité : Max Jaderberg · Anime : Marina MogilkoThe researcher explains virtual screening, real laboratory checks and why agent performance must be measured against useful outcomes.
38:50EN
AI Engineer· 10 nov. 2026LinkedIn’s self-improving agent first had to fix its judgesZiwei Guo, Saloni Gandhi · LinkedInA prompt-optimization loop improved a career agent, but unreliable evaluators required human calibration first.
12:48ENAI Engineer· 10 nov. 2026Brian Douglas: Turn agent corrections into reusable review knowledgeBrian Douglas · Paper ComputeThe Paper Compute developer captures expert pushback in coding sessions and tests ways to reuse it during review.
59:06EN
a16z· 10 nov. 2026Dharmesh Shah: Find startup opportunities beyond the AI labs’ pathJoe Schmidt, Dharmesh Shah · Andreessen HorowitzHubSpot’s co-founder explains how to test narrow ideas, build around customer work and use AI without relying on a temporary model gap.
12:20ENAI Engineer· 10 nov. 2026Ayush Bhardwaj: Agent workarounds are feedback for your CLIAyush Bhardwaj · Allos AIAn audit of coding sessions shows where output, errors and stale instructions force agents to improvise.
1:46:17EN
The Knowledge Project Podcast· 10 nov. 2026Podcast · 2 voixJon McNeill on Tesla’s speed: delete steps before automatingInvité : Jon McNeill · Anime : Shane ParrishThe former Tesla president explains the sales bottleneck, product feedback and five-step simplification method behind rapid growth.
23:03EN
Masters of Scale· 10 nov. 2026Podcast · 3 voixTubi and e.l.f. grew by serving audiences incumbents overlookedInvité : Anjali Sud, Kory Marchisotto · Anime : Bob SafianAnjali Sud and Kory Marchisotto explain free streaming, affordable beauty and direct feedback from fans.
43:05EN
The Builders· 10 nov. 2026Alex Karp says AI could widen inequality—and rejects a wealth taxInvité : Alex Karp · Anime : Walter IsaacsonThe Palantir CEO links data sovereignty, surveillance limits and a proposed tax-and-efficiency trade-off.
12:57ENAI Engineer· 10 nov. 2026Harvey’s agents scaled until their platform and merge queue brokeJoey Wang · HarveyAfter an alert spawned 900 agents and one engineer launched 950 tasks, Harvey added deduplication and fair scheduling.
31:18EN
Hard Fork· 10 nov. 2026Podcast · 2 voixNvidia’s board investigates reports involving Jensen HuangInvité : Stephen Witt · Anime : Max ReadJournalist Stephen Witt discusses leadership risk, export controls and unanswered questions around Megaspeed.
51:48ENAI Engineer· 10 nov. 2026Compose small decisions before reaching for a generative modelRaymond Weitekamp · OpenProseRaymond Weitekamp demonstrates recursive decision models and sketches a voice-first computer interface.
23:00ENAI Engineer· 10 nov. 2026A passing PR check needs evidence tied to the submitted codeStephen Chin, Cassandra Chin · Neo4jStephen and Cassandra Chin show how Tracetoon connects agent traces, code changes and checks before writing a reviewable pull request.
22:49ENAI Engineer· 10 nov. 2026When many coding agents share one codebase, delivery must handle concurrencyPatrick Debois · TesslPatrick Debois explains how shared planning, merge strategies and risk-based review can help teams coordinate agents.
23:57EN
Google Cloud Tech· 10 nov. 2026Six front-end ideas that make AI-built apps easier to debugDevin Chasanoff · Google CloudDevin Chasanoff uses an interactive game tracker to show where data lives, how values are derived and how components communicate.
38:07EN
GOTO Conferences· 10 nov. 2026A smoother reorganization starts by letting teams design itJoakim Sundén · Better Product WorkJoakim Sundén pairs leadership’s strategy with employees’ knowledge of daily work, then lets people select teams.
1:25:52EN
Latent Space· 10 nov. 2026Podcast · 2 voixZeno Rocha on building email tools for people and agentsInvité : Zeno Rocha · Anime : Shawn WangThe Resend co-founder explains deliverability, agent-facing interfaces and why he writes product information for machines to read.
15:41ENAI Engineer· 10 nov. 2026Meta’s on-call AI teammate earns autonomy one action at a timeChinmay Gandhi, Swaapnika Motapothula, Vlad Tsvang · MetaThe team connects incident context and shared memory while keeping critical decisions and code review with people.
14:30ENAI Engineer· 10 nov. 2026Why reading a skill file cannot reveal everything an agent will doRoey Ben Chaim · ZenityZenity’s Roey Ben Chaim describes sandbox testing that follows dependencies and observes process, file and network activity.
1:17:53EN
Stanford Online· 10 nov. 2026How language-model design shapes context engineering for agentsMichael Ryan · Stanford UniversityStanford’s Michael Ryan connects decoding, attention and inference to the practical choices agent builders make.
20:06ENAI Engineer· 10 nov. 2026Prasanna Sankar: As agents write more code, coordination becomes the bottleneckPrasanna Sankar · VorfluxThe Vorflux founder describes cloud environments, review and merge queues, and agents that help initiate routine work.
1:16:16ENStanford Online· 10 nov. 2026Cynthia Bailey: Prompt clearly, verify evidence and keep your own judgmentCynthia Bailey · Stanford UniversityThe Stanford lecturer explains practical prompting, context management and ways to prevent skills from quietly fading.
1:25:20EN
The Pragmatic Engineer· 10 nov. 2026Podcast · 2 voixSean Allen: Make software correctness part of the designInvité : Sean AllenThe Antithesis engineer argues for earlier guarantees, more thoughtful test workloads and planning for production failures.
28:00ENAI Engineer· 10 nov. 2026Robinhood’s AI reviewer merges 60% of data PRs without human reviewChetas Joshi · RobinhoodScripts verify live facts, an agent traces code risks, and people retain sensitive decisions.Charger plus24 sur 6 204 affichés