最新の記事
4,467 件並び順
16:14ENAGI Timelines and AI Safety Commitments: The 2023 DebateA historical comparison of forecasts, the Bletchley summit and research on model behavior.
1:16:06ENDavid Meyer on Product Management, Customer Curiosity and Building Teamsゲスト David Meyer · ホスト Harry StebbingsThe Databricks product leader explains why product work is a balancing act, how to test assumptions with customers, and what he looks for when hiring.
1:32:40ENThe Historian Who Taught GPT-3.5 to Beat GPT-4ホスト Nathan LabenzMark Humphries on a kilometer of unread paper, fur-trade jargon that embeddings cannot see, and why cheap processing will force history to be rewritten.
5:31ENConnecting MemGPT to AutoGen AgentsMatthew Berman · Forward FutureIn a 2023 tutorial, Matthew Berman configures a MemGPT-backed coding agent alongside an AutoGen product manager and runs a short group chat.
1:16:45ENNick Tomaino on Crypto Investing, FTX and the NFT Debateゲスト Nick Tomaino · ホスト Harry StebbingsThe 1confirmation founder discusses fund discipline, token incentives, OpenSea and the limits of conviction in a 2023 conversation.
17:11ENNext.js 14 in Context: Server Actions and Partial PrerenderingTheo Browne · Ping LabsTheo explains the 2023 release and its rendering tradeoffs.
10:13ENBuilding a Business Chatbot with GPTBots.aiMatthew Berman · Forward FutureIn a sponsored 2023 walkthrough, Matthew Berman configures an assistant, adds business knowledge, corrects a response and builds a branching flow.
50:31ENEd Sim on Seed Valuations, Inception Investing and Reserving for Growthゲスト Ed Sim · ホスト Harry StebbingsThe Boldstart founder explains his early financing framework, the risks of excess capital and why follow-on discipline matters.
6:40ENRunning MemGPT with an Open-Weight Model on RunPodMatthew Berman · Forward FutureMatthew Berman connects the original MemGPT project to a model served through text-generation-webui, then tests a simple memory interaction. The demonstration uses a remote GPU and historical software versions.
36:22ENOne Attacker and a For Loop: Why Email Is Still the Softest Target in an AI Arms Raceホスト Sarah Guo, Elad GilMaterial Security co-founder Ryan Noon on how 2016 election hacks, Google and Microsoft's email duopoly, and large language models are rewriting both sides of cybersecurity.
38:07ENAutoGen Advanced Tutorial: Configuration, Memory, Retrieval and ToolsMatthew Berman · Forward FutureMatthew Berman walks through the 2023 AutoGen interface for multi-agent configuration, caching, retrieval, teachable memory and function calls.
1:25:11EN105 lines of code, a million impressions, and a VC who refused to found the companyホスト Nathan LabenzBabyAGI creator Yohei Nakajima tells Nathan Labenz how a weekend prototype set off the agent wave — and why he went back to writing checks.
1:01:06ENEly Lerner on Startup Advisors, Growth Strategy and Focusゲスト Ely Lerner · ホスト Harry StebbingsThe former Yelp and Chime product leader explains how to choose and compensate advisors, identify a growth lever, and balance strategic bets with essential defensive work.
26:40ENMatthew Prince and Harry Stebbings Debate How Narrowly Startups Should Focusゲスト Matthew Prince · ホスト Harry StebbingsThe Cloudflare co-founder and 20VC host examine early customers, ambitious visions and the different goals of venture-backed and bootstrapped companies.
1:26:30ENMost of this data has never been in a database: Chroma's wartime CTO on RAGホスト Nathan LabenzAnton Troynikov returns to The Cognitive Revolution to argue that retrieval quality is mostly the embedding, that Chroma should own the RAG loop, and that GPT still fails a basic Game of Life test of reasoning.
53:34ENMatthieu Rouif on PhotoRoom's Focus, Mobile Growth and AI Designゲスト Matthieu Rouif · ホスト Harry StebbingsThe PhotoRoom co-founder explains how user testing, a narrow audience and mobile distribution shaped the photo-editing business.
32:34ENTen Thousand Certified Engineers in a Year: Google Cloud's Order of Operations for Enterprise AIホスト Sarah Guo, Elad GilKawal Gandhi, head of generative AI in Google Cloud's Office of the CTO, walks Sarah Guo and Elad Gil through dogfooding, the efficiency-productivity-creativity ladder, and why customer weights are the IP that cannot leak.
32:14ENMemGPT: Managing LLM Memory Beyond a Fixed Context WindowMatthew Berman, Charles Packer, Vivian Fang · Forward FutureMatthew Berman reviews the 2023 research, demonstrates document retrieval and hears from authors Charles Packer and Vivian Fang about their plans.
1:19:52EN1,000 H100s Take 115 Days; 22,000 Take Fiveホスト Nathan LabenzNathan Labenz and Trey Kollmer walk through cluster math that turns GPT-4-scale training into a weekly experiment, then four papers on search-augmented models, recursive code improvers, spatial maps inside Llama 2, and what networks do when they have no idea.
1:00:35ENBeezer Clarkson on LP Liquidity, Venture Returns and Fund Incentivesゲスト Beezer Clarkson · ホスト Harry StebbingsThe Sapphire Partners investor explains how LPs assess managers, fund size and distributions during a difficult 2023 fundraising market.
7:02ENConnecting AutoGen to a RunPod-Hosted Model with Text Generation WebUIMatthew Berman · Forward FutureIn a 2023 walkthrough, Matthew Berman connects AutoGen to Dolphin 2.1 Mistral 7B through an OpenAI-compatible API and tests a small coding task.
0:24ENMichael Eisenberg on Social Media and His Family During Warゲスト Michael EisenbergA brief October 2023 perspective on technology, violent imagery and the personal cost of conflict.
4:42ENConnecting AutoGen to a Local Model With LM StudioMatthew Berman · Forward FutureMatthew Berman demonstrates an early local-model setup and explains where agent behavior still needs work.
1:07:13ENMatthew Prince on Co-Founders, Ambition and Cloudflare’s Early Growthゲスト Matthew Prince · ホスト Harry StebbingsThe Cloudflare co-founder debates whether venture-backed startups should target a narrow first customer, and reflects on partnerships, risk and success.
もっと見る4,467 件中 24 件を表示









