Résultats
27 articlesTrier
56:01EN
AI Engineer· 26 oct. 2026Xander Song on Evaluating Agents with Harbor and PhoenixXander Song · Arize AIArize AI engineer Xander Song explains how Harbor runs realistic agent tasks in isolated sandboxes, and how his team uses Phoenix to compare prompt changes, inspect trajectories, and test a SQL tool.
35:19ENAI Engineer· 25 oct. 2026SallyAnn DeLucia: How to Write Your First AI EvalSallyAnn DeLucia · Arize AITurn an agent’s real traces into concrete pass/fail criteria, then build an LLM judge you can test, align with people, and run in production.
12:31ENJev's Fast Decisions: Demos, Tradeoffs and Reliability ClaimsMatthew Berman · Forward FutureMatthew Berman explores a decision-oriented AI model through routing, simulated worlds, chess and game-control examples.
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.
36:19EN
No Priors: AI, Machine Learning, Tech, & Startups· 26 juin 2026Podcast · 2 voixThe Benchmark Grid Is Broken: Why Test-Time Compute Has Outrun How We Score ModelsAnime : Sarah Guo, Elad GilOpenAI researcher Noam Brown argues that static leaderboards hide how long a model is allowed to think — and that safety evals, research taste, and the release cycle have not caught up.
48:00EN
Unsupervised Learning: With Jacob Effron· 15 déc. 2025PodcastA Two-Second Vote Is Training Models to Be ClickbaitAnime : Jacob EffronSurge AI CEO Edwin Chen tells Redpoint why LMArena rewards length and emojis, how one lab's models got worse for a year, and why frontier labs are no longer on the same path.
32:59ENNo Priors: AI, Machine Learning, Tech, & Startups· 24 juil. 2025Podcast · 2 voixA Hundred People, a Billion in Revenue, and Zero Venture MoneyAnime : Sarah Guo, Elad GilSurge AI founder Edwin Chen on why quality human data is a poetry problem, not a bounding-box problem, and why leaderboards keep training models to write clickbait.
47:07EN
Sequoia Capital· 8 juil. 2025PodcastGoodfire’s Eric Ho thinks we will decode neural nets by 2028On Sequoia’s Training Data, the interpretability founder argues that sparse autoencoders, model editing, and a third-party lab are how AI stops being grown from data and starts being designed.
40:33ENSequoia Capital· 24 juin 2025PodcastFifty People in Slack. Four Minutes to the Smoking Gun.Traversal's co-founders on turning DevOps heart attacks into agent-run root cause analysis — and why observability's second-largest software spend still leaves troubleshooting as a whodunit.
54:53ENUnsupervised Learning: With Jacob Effron· 17 juin 2025PodcastA Free Voting Board Burned $2 Million. Then It Raised $100 Million.Anime : Jacob EffronDatabricks co-founder Ion Stoica explains why LMArena exists, why China is winning open-source models, and why reliability—not another scaling law—is still the thing holding AI back.
44:21ENUnsupervised Learning: With Jacob Effron· 4 juin 2025PodcastMercor's CEO: Knowledge Work's Next Job Is Writing EvalsAnime : Jacob EffronBrendan Foody tells Redpoint how Mercor turned AI hiring and expert data into a $100 million round — and why he thinks a huge slice of white-collar work will become creating tests for models.
57:11ENUnsupervised Learning: With Jacob Effron· 30 janv. 2025PodcastA Million Tokens Cannot Write a Good JokeAnime : Jacob EffronPrinceton's Arvind Narayanan on why agent evals mislead, inference scaling hits a wall, and AI looks more like the internet than an overnight revolution.
1:46:41ENCognitive Revolution "How AI Changes Everything"· 21 déc. 2024PodcastFrontier Models Hit the 10th–40th Percentile on Real AI R&DAnime : Nathan LabenzNeev Parikh of METR walks Nathan Labenz through REBench, a seven-task test of whether agents can do machine learning research—and what happened when one of them decided not to train.
1:23:37ENCognitive Revolution "How AI Changes Everything"· 23 oct. 2024PodcastNine of the top ten research ideas were Claude'sAnime : Nathan LabenzStanford PhD student Chenglei Si ran a blind study pitting Claude 3.5 Sonnet against more than a hundred NLP researchers on novel research ideas.
38:28ENNo Priors: AI, Machine Learning, Tech, & Startups· 8 oct. 2024Podcast · 2 voixHalf of Production AI Is RAG. Fine-Tuning Almost Disappeared.Anime : Sarah Guo, Elad GilBraintrust CEO Ankur Goyal tells No Priors what Notion, Zapier, and Vercel actually ship — and which hyped techniques they quietly dropped.
1:54:17ENCognitive Revolution "How AI Changes Everything"· 28 août 2024PodcastMetaculus Flagged Covid in January 2020. Now It Is Putting AI on the Forecasting DeskAnime : Nathan LabenzNathan Labenz talks with Metaculus CEO Deger Turan about epistemic security, a year-long bot tournament, and why a useful forecast is harder than an accurate one.
1:56:03ENCognitive Revolution "How AI Changes Everything"· 13 juil. 2024PodcastHumans Near a Perfect Score. The Best AI Still Gets 39%Anime : Nathan LabenzZapier co-founder Mike Knoop and François Chollet put $1 million on ARC-AGI, a 2019 test of sample-efficient intelligence that language models still cannot crack under a one-cent-per-puzzle budget.
55:13ENSequoia Capital· 2 juil. 2024PodcastThe Best AI Scores 39% on This Test. Zapier’s Co-Founder Put $1 Million on Beating ItFrançois Chollet designed ARC to measure skill-acquisition efficiency; five years later humans still crush it and frontier models do not.
26:00ENNo Priors: AI, Machine Learning, Tech, & Startups· 11 juin 2024Podcast · 2 voixWhy a Zapier founder thinks AGI research has been stalled for four yearsAnime : Sarah Guo, Elad GilMike Knoop and François Chollet put more than a million dollars on beating ARC-AGI, the eval they say actually measures general intelligence.
43:45ENNo Priors: AI, Machine Learning, Tech, & Startups· 3 août 2023Podcast · 2 voixEight Years of No Growth, Then OpenAI and NVIDIA Became His CustomersAnime : 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.
44:19ENNo Priors: AI, Machine Learning, Tech, & Startups· 15 juin 2023Podcast · 2 voixAI Will Write Ten Times More Code. Someone Still Has to Keep It Running.Anime : Sarah Guo, Elad GilDatadog co-founder Olivier Pomel on why faster generation moves value from writing software to understanding, securing, and operating it.
53:37ENNo Priors: AI, Machine Learning, Tech, & Startups· 9 mars 2023Podcast · 2 voix30 models, 42 scenarios, 7 metrics: Percy Liang's public checkup for language modelsAnime : Sarah Guo, Elad GilA PubMed-only model once led the U.S. medical licensing exam — until a system roughly 200 times larger overtook it.
2:34:20EN
Lex Fridman· 30 août 2020Podcast · 2 voixIntelligence Is How Efficiently You Acquire Skills You Were Not Prepared ForInvité : François Chollet · Anime : Lex FridmanFrançois Chollet tells Lex Fridman why skill is not intelligence, why GPT-3 is still pattern matching, and why a grid puzzle called ARC still separates children from machines.
1:07:08EN
Lenny's PodcastPodcast · 2 voixIf the Model Is the Product, the Eval Is the PRD: Inside Mercor's RiseInvité : Brendan Foody · Anime : Lenny RachitskyMercor CEO Brendan Foody explains why AI labs will pay almost anything for expert-written evals, how his company grew from $1 million to a $400 million run rate in 16 months, and what that means for jobs and founders.Charger plus24 sur 27 affichés