YoutuBlog (HackerTube): read YouTube talks and podcasts
Latest articles
6,220 articlesSort
25:17EN
Peter Yang· Nov 11, 2026PodcastPeter Yang splits Claude Code work between Opus and FableHe uses Opus for routine execution and reserves Fable for harder decisions, code audits and family-care coordination.
19:44EN
OpenAI· Nov 11, 2026What a managed agent harness has to do to keep workingCharlie, Steve · OpenAIOpenAI engineers explain remote sandboxes, long-running state and a human-approved flight rebooking demo.
1:24:54EN
Invest Like The Best· Nov 11, 2026Podcast · 2 speakersZach Reitano: US healthcare must answer to patientsGuest Zach Reitano · Host Patrick O'ShaughnessyRo's founder argues for transparent prices and patient choice, and describes the company's 2022 reset.
1:13:14EN
Reid Hoffman· Nov 11, 2026Podcast · 3 speakersRonnie Chatterji: AI may change work before it changes job countsGuest Ronnie Chatterji · Host Reid Hoffman, Aria FingerOpenAI’s chief economist expects productivity gains, but says attributing them to AI and managing uneven effects will take work.
27:14EN
Bloomberg Live· Nov 11, 2026John Kerry: Cheaper clean energy needs faster deploymentAaron Rutkoff, John Kerry · BloombergKerry argues clean energy can compete on price, while warning that permitting delays and climate damage add costs.
59:16EN
Conversations with Tyler· Nov 11, 2026Podcast · 2 speakersTerence Tao: AI proofs make mathematical understanding more urgentGuest Terence Tao · Host Tyler CowenTao explains why proof abundance may change research, education and the value of human explanation.
26:47EN
Every· Nov 11, 2026Podcast · 2 speakersDan Shipper: AI makes generating ideas cheap; people still choose what mattersHost Natalia QuinteroThe Every co-founder uses one customer survey to explain why different perspectives can produce different work from the same model.
27:09ENOpenAI· Nov 11, 2026A six-week coding agent run and what it took to superviseOpenAI engineers describe a CI maintenance agent, long-running context and the cost of keeping it working.
20:48ENOpenAI· Nov 11, 2026Sites adds personalized connectors and agent-friendly web appsKatia, John · OpenAIOpenAI demonstrates scheduled updates, per-user plugins and WebMCP in two Sites applications.
29:37EN
Theo - t3․gg· Nov 11, 2026Theo finds a security use for Gemini 4 Carbon despite coding frustrationsTheoHis tests show fewer false code-analysis claims than Argon, but latency and reliability still push him toward other models.
21:35EN
Masters of Scale· Nov 11, 2026Podcast · 2 speakersEric Ries: Why successful companies lose the purpose that made them workGuest Eric Ries · Host Krista TippettRies argues that pressure from capital can erode a company’s mission, and that trust deserves a place in business decisions.
56:06EN
a16z· Nov 11, 2026Mike Volpi: AI infrastructure can endure a market correctionRaghu Raghuram, Guido Appenzeller, Mike Volpi · Andreessen HorowitzThe former Cisco executive sees useful assets beyond the hype, but questions who will own them and how systems will evolve.
1:42:10EN
Jane Street· Nov 11, 2026How quickly could AI improve itself? Four forecasters disagreeYaron Minsky, Jaime Sevilla, Ege Erdil, Ryan Greenblatt, Daniel Kokotajlo · Jane StreetOne forecaster puts AI research automation at 50% by 2028; another sees a slower path as more likely, with a real chance of rapid progress.
18:18EN
Matthew Berman· Nov 11, 2026Fable 5.2 leads a week of model releases, but cost changes the choiceMatthew Berman · Forward FutureMatthew Berman compares Fable and Gemini Carbon, reviews smaller models and discusses Nvidia’s investigation.
12:38EN
AI Engineer· Nov 11, 2026How Duolingo uses agents to add tests without skipping human reviewKush Agrawal · DuolingoA scheduled pipeline raised iOS coverage by generating tests, repairing CI and routing pull requests to engineers for approval.
1:03:19EN
Stanford Online· Nov 11, 2026Manage AI sources: retrieve selectively and withhold context when usefulCynthia Bailey · Stanford UniversityStanford lecturer Cynthia Bailey explains when to retrieve documents, leave context out and guard against instructions hidden in sources.
2:55:43EN
PowerfulJRE· Nov 11, 2026Podcast · 3 speakersPaddy Pimblett on fighting, weight cuts and the lightweight divisionGuest Paddy Pimblett · Host Joe RoganPimblett explains his Saint Denis finish, his difficult recovery from ankle surgery, and why he refuses to fight teammates.
48:20ENTheo - t3․gg· Nov 10, 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· Nov 10, 2026Isomorphic Labs’ Max Jaderberg on narrowing drug designs with AIGuest Max Jaderberg · Host Marina MogilkoThe researcher explains virtual screening, real laboratory checks and why agent performance must be measured against useful outcomes.
38:50ENAI Engineer· Nov 10, 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· Nov 10, 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.
59:06ENa16z· Nov 10, 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· Nov 10, 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· Nov 10, 2026Podcast · 2 speakersJon McNeill on Tesla’s speed: delete steps before automatingGuest Jon McNeill · Host Shane ParrishThe former Tesla president explains the sales bottleneck, product feedback and five-step simplification method behind rapid growth.Load moreShowing 24 of 6,220