Résultats
198 articlesTrier
9:43EN
Matthew Berman· 26 août 2024Matthew Berman Tests Jamba 1.5 on Coding and Reasoning PromptsMatthew Berman · Forward FutureA 2024 hands-on test of AI21’s hybrid model finds slow output in one hosted session and mixed answers to a small set of prompts.
12:17ENMatthew Berman· 7 août 2024Testing Gemini 1.5 Pro on Code, Reasoning, Images and VideoMatthew Berman · Forward FutureMatthew Berman compares standard and experimental Gemini versions in an informal 2024 review, finding mixed results and repeated output errors.
42:08EN
Sequoia Capital· 30 juil. 2024PodcastMeta Trained a 405B Teacher on 16,000 GPUs — Then Told the World to Distill ItTwo days after Llama 3.1 405B shipped, Meta's generative-AI product lead walks Sequoia through why the most expensive model in the family is free, and why he thinks the frontier itself is heading toward commodity.
13:40ENMatthew Berman· 29 juil. 2024Testing Llama 3.1 8B: Benchmark Gains and Mixed Practical ResultsMatthew Berman · Forward FutureMatthew Berman tests coding, reasoning and other prompts on the small model and finds several failures despite stronger reported benchmarks.
25:56EN
No Priors: AI, Machine Learning, Tech, & Startups· 11 juil. 2024Podcast · 2 voixA Prompt Cannot Hold a Good Design: Six AI Practitioners at Midyear 2024Anime : Sarah Guo, Elad GilSarah Guo and Elad Gil stitch together clips from Stripe, Figma, Figure, OpenAI's Sora team, Cognition, and Scale into a half-year snapshot of what people actually shipping AI were willing to claim.
1:16:22EN
Cognitive Revolution "How AI Changes Everything"· 9 juil. 2024PodcastHe Spent 20 Hours Crafting a Prompt. DSPy Beat Him AnywayAnime : Nathan LabenzSander Schulhoff walks through The Prompt Report — a 78-page survey of what actually works when you prompt large language models.
8:53ENMatthew Berman· 8 juil. 2024RouteLLM: Routing Queries Between Strong and Cheaper ModelsMatthew Berman · Forward FutureMatthew Berman explains a 2024 research framework that uses preference data to choose a model for each query.
59:11ENSequoia Capital· 25 juin 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%.
10:57ENMatthew Berman· 24 juin 2024Testing Claude 3.5 Sonnet: Coding, Reasoning, and VisionMatthew Berman · Forward FutureMatthew Berman puts Anthropic’s June 2024 model through informal coding, math, puzzle, and image-understanding prompts.
1:37:07ENCognitive Revolution "How AI Changes Everything"· 22 juin 2024PodcastA Text-Only AI Outdiagnosed GPs. Google Still Won't Ship It.Anime : Nathan LabenzGoogle researchers Vivek Natarajan and Khaled Saab walk Nathan Labenz through five medical-AI papers, from radiology reports to an AI doctor that still has to earn trust.
1:25:10ENCognitive Revolution "How AI Changes Everything"· 15 juin 2024PodcastA Tenth of Google's Index, 99.9% Recall: How 20 People Built Brave SearchAnime : Nathan LabenzJosep M. Pujol walks Cognitive Revolution through Brave's privacy-first index, hybrid retrieval stack, and the Search API Nathan Labenz now wants his own product team to use.
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.
58:28ENCognitive Revolution "How AI Changes Everything"· 22 mai 2024PodcastFrom Jailbreaking ChatGPT to Anthropic’s First Prompt Engineer: How Alex Albert Ships Claude 3Anime : Nathan LabenzA year after building jailbreakchat.com, Alex Albert walks Nathan Labenz through Claude 3’s writing, orchestration, character work, and the guardrails app developers still skip.
39:00ENNo Priors: AI, Machine Learning, Tech, & Startups· 22 mai 2024Podcast · 2 voixJPMorgan Has 150 Petabytes. GPT-4 Trained on Less Than One.Anime : Sarah Guo, Elad GilScale AI founder Alexandr Wang tells No Priors why easy internet data is exhausted, why expert-plus-model teams still win, and why the path to AGI looks more like curing cancer than inventing a vaccine.
12:50ENMatthew Berman· 22 mai 2024Testing Smaug: Hosted 70B Versus a Smaller Local ModelMatthew Berman · Forward FutureMatthew Berman compares two Smaug configurations on Snake, math and reasoning puzzles.
54:25ENCognitive Revolution "How AI Changes Everything"· 9 mai 2024PodcastJail Only for Perjury: Scott Wiener Walks Through California's Frontier AI BillAnime : Nathan LabenzSB 1047 sets the same 10^26 FLOPs threshold as the Biden executive order, and the San Francisco senator wants testing without a licensing regime.
1:05:52ENCognitive Revolution "How AI Changes Everything"· 3 mai 2024PodcastInfinite AI Interns Are Already on the JobAnime : Nathan LabenzNathan Labenz tells computer-science students how to stand out when models are beating doctors on routine work and firms are hiring fewer juniors.
16:28ENMatthew Berman· 23 avr. 2024Testing Reka Core: Multimodal Benchmarks, Coding and ReasoningMatthew Berman · Forward FutureMatthew Berman reviews Reka’s reported model comparisons and tests Core on code, logic and image understanding.
15:01ENMatthew Berman· 19 avr. 2024Testing Llama 3 at Launch: Code, Reasoning and Image GenerationMatthew Berman · Forward FutureMatthew Berman tries Meta AI’s new interface on a snake game, logic puzzles and rapid image generation.
24:32ENNo Priors: AI, Machine Learning, Tech, & Startups· 18 avr. 2024Podcast · 2 voixImage Generation Is Still a Loot Box. Suhail Doshi Wants to Scale PixelsAnime : Sarah Guo, Elad GilThe Playground AI founder tells No Priors why he skipped language models, how a noise-sampling trick fixed SDXL's muddy brightness, and what a large vision model would actually do.
13:59ENMatthew Berman· 5 avr. 2024SWE-agent Tutorial: Navigating Repositories and Attempting GitHub FixesMatthew Berman, Carlos · Forward FutureMatthew Berman sets up a research coding agent, hits an installation problem and a cost limit, then shows an author’s successful SymPy benchmark example.
1:23:09ENCognitive Revolution "How AI Changes Everything"· 3 avr. 2024PodcastThe Right Size of an AI Task Is Whatever You Can CheckAnime : Nathan LabenzElicit founders Andreas Stuhlmüller and Jungwon Byun walk through how a twelve-person research assistant cut summary hallucinations from 1.5 to 0.5, ships about every week and a half, and treats task decomposition as the way to spend more compute without a black box.
9:02ENMatthew Berman· 1 avr. 2024Matthew Berman Tries LLM Colosseum, a Street Fighter Model BenchmarkMatthew Berman · Forward FutureA 2024 tutorial shows language models choosing fighting-game moves, explains the game-state prompt and walks through local setup.
14:23ENMatthew Berman· 31 mars 2024Testing DBRX: Coding Strengths and Reasoning GapsMatthew Berman · Forward FutureMatthew Berman examines Databricks’ open-weight model and puts it through coding, arithmetic and reasoning prompts.Charger plus24 sur 198 affichés