Chaînes mises à jour récemment

Choisissez-en une pour ne voir qu’elleToutes les chaînes →

Résultats

326 articles
Trier
4 diapositives7:48EN
Matthew Berman· 26 nov. 2023Testing Dolphin 2.2 Yi 34B on Coding and Reasoning TasksMatthew Berman · Forward FutureMatthew Berman runs a quantized Yi fine-tune through informal coding, writing and logic prompts in November 2023, with uneven results.Open-weight modelsFoundation ModelsBenchmarks+2
32:48EN
No Priors: AI, Machine Learning, Tech, & Startups· 16 nov. 2023Podcast · 2 voixFourteen People, $200 Million of Compute, and the Reliability Bottleneck for AgentsAnime : Sarah Guo, Elad GilImbue co-founders Kanjun Qiu and Josh Albrecht on why agents fail, why language models cannot learn general algorithms, and why they are spending a giant round on GPUs rather than headcount.AgentsAgents de codeIngénierie d’agents+3
3 diapositives5:31EN
Matthew Berman· 30 oct. 2023Connecting 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.Agent memoryMulti-agent systemsAgents de code
4 diapositives7:02EN
Matthew Berman· 18 oct. 2023Connecting 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.Ingénierie d’agentsOpen-weight modelsMulti-agent systems+2
5 diapositives15:03EN
Matthew Berman· 10 oct. 2023A 2023 AutoGen Tutorial: Local Agent Setup and Code ExecutionMatthew Berman · Forward FutureMatthew Berman builds a local assistant and user-proxy workflow, then tests how the agents generate and run Python. AutoGen’s packages and APIs have changed since this tutorial.Multi-agent systemsIngénierie d’agentsAgents de code+2
1:32:41EN
Cognitive Revolution "How AI Changes Everything"· 5 oct. 2023PodcastThere are maybe 5,000 people who can train frontier models. The rest need AI engineersAnime : Nathan LabenzSwyx of Latent Space tells Nathan Labenz how a new job is forming, why OpenAI will Sherlock its developers, and what still does not count as an agent.Entreprise et stratégieIngénierie d’agentsAgents de code+3
3 diapositives7:32EN
Matthew Berman· 4 oct. 2023MageGPT Generates a Wasp To-Do App: A 2023 DemonstrationMatthew Berman · Forward FutureMatthew Berman uses a Wasp-sponsored app generator to build, run and deploy a basic full-stack to-do app.Agents de codeSoftware engineeringWorkflows de développement et tests
6 diapositives18:23EN
Matthew Berman· 2 oct. 2023Early ChatGPT Vision Examples: From Diagrams to Code and Visual MistakesMatthew Berman · Forward FutureMatthew Berman surveys 2023 image-input demonstrations, including education, design and programming, and examines examples that were not verified or got details wrong.Computer VisionMultimodal AIEducation+2
2:17:30EN
Cognitive Revolution "How AI Changes Everything"· 29 sept. 2023PodcastGemini Became the Daily Driver. A GPT-5 Worthy of the Name Would Make Agents Work.Anime : Nathan LabenzZvi Mowshowitz returns to Cognitive Revolution to unpack Gemini 1.5, Sora, superalignment, sleeper agents, and the live-player map of frontier labs.Entreprise et stratégieAI StrategyProduct Strategy+3
29:38EN
No Priors: AI, Machine Learning, Tech, & Startups· 21 sept. 2023Podcast · 2 voixA Beginner Just Shipped a $250K Business. Professionals Got 30 Percent.Anime : Sarah Guo, Elad GilReplit CEO Amjad Masad on Ghostwriter, why a 3-billion-parameter model was enough, and the agents he wants earning bounties while you sleep.Agents de codeDeveloper productivityOpen-weight models+3
4 diapositives9:59EN
Matthew Berman· 7 sept. 2023Open Interpreter: A 2023 Local Code-Execution WalkthroughMatthew Berman · Forward FutureMatthew Berman installs Open Interpreter, analyzes local files with GPT-4 and tries a local Code Llama setup, with mixed results.Agents de codeLocal inferenceWorkflows de développement et tests+2
4 diapositives4:35EN
Matthew Berman· 5 sept. 2023Running WizardCoder on a Cloud GPU: A 2023 RunPod WalkthroughMatthew Berman · Forward FutureMatthew Berman demonstrates downloading a quantized 13B coding model into a hosted text-generation interface, then explains how to stop the pod and avoid ongoing charges.Modèles et entraînementInfrastructure et déploiementAgents de code
3 diapositives14:59EN
Matthew Berman· 2 sept. 2023AI News in September 2023: Tesla, Code Llama, Drone Racing and CopyrightMatthew Berman · Forward FutureMatthew Berman surveys a week of AI announcements, from Tesla's driving demonstration and ChatGPT Enterprise to model releases, generative media and a copyright inquiry.AI StrategyAgents de codeAutonomous Driving+2
3 diapositives6:11EN
Matthew Berman· 31 août 2023Running WizardCoder Locally with Text Generation WebUIMatthew Berman · Forward FutureMatthew Berman walks through a 2023 setup for a quantized Code Llama-based coding model, from the Python environment to a simple test prompt.Local inferenceAgents de codeOpen-weight models+1
5 diapositives10:20EN
Matthew Berman· 30 août 2023Phind Code Llama 34B vs GPT-4: A 2023 Python Coding TestMatthew Berman · Forward FutureMatthew Berman compares a quantized Phind fine-tune with GPT-4 on games, short functions and refactoring, with mixed results.Open-weight modelsAgents de codeÉvaluations+2
1:39:53EN
Cognitive Revolution "How AI Changes Everything"· 8 août 2023PodcastUnder 100 People, 24 Million Users: Replit's Bet on Artificial Developer IntelligenceAnime : Nathan LabenzMichele Catasta, Replit's new VP of AI, lays out a generate-execute-learn loop he will not call AGI, a 2x-to-1000x productivity ladder, and a keystroke-level data advantage.Agents de codeDeveloper productivityAI startups & small teams+3
1:45:46EN
Cognitive Revolution "How AI Changes Everything"· 4 août 2023PodcastReplit's $10 AI Programmer Already Pays for Itself. The Ambition Is Bots Hiring BotsAnime : Nathan LabenzTyler Angert, Replit's first product designer, explains Ghostwriter, a virtual developer, and why the company calls itself the perfect substrate for AGI.Agents de codeDeveloper productivityProduct Strategy+3
4 diapositives11:07EN
Matthew Berman· 24 juil. 2023Installing Llama 2 13B Chat and Testing Its ResponsesMatthew Berman · Forward FutureMatthew Berman demonstrates a 2023 local setup and tests a 13-billion-parameter chat model on coding, writing, arithmetic and reasoning. His small set of prompts illustrates both useful outputs and mistakes.Local inferenceOpen-weight modelsÉvaluations+2
3 diapositives12:20EN
Matthew Berman· 10 juil. 2023Testing UltraLM 13B: A Small Model’s Strengths and Reasoning ErrorsMatthew Berman · Forward FutureA 2023 local test finds useful writing and simple coding alongside failures in games, arithmetic and logic.Open-weight modelsÉvaluationsModèles et entraînement+1
3 diapositives7:05EN
Matthew Berman· 2 juil. 2023Aider’s Early Coding Assistant: Snake and an Existing Rails ProjectMatthew Berman · Forward FutureMatthew Berman demonstrates the terminal tool’s 2023 workflow, from generating and iterating on a game to proposing a dependency change in a repository.Agents de codeWorkflows de développement et testsSoftware engineering+1
4 diapositives6:26EN
Matthew Berman· 14 juin 2023Installing and Trying GPT-Engineer: A 2023 Snake Game WalkthroughMatthew Berman · Forward FutureMatthew Berman demonstrates the early project-generation workflow, from a Conda environment and prompt to clarification questions and generated Python files.Agents de codeWorkflows de développement et testsSoftware engineering
5 diapositives7:37EN
Matthew Berman· 25 mai 2023Smol Developer: Generating a Small Python Project From a PromptMatthew Berman · Forward FutureMatthew Berman walks through a 2023 project generator, from a simple Ruby example to a multi-file ChatGPT API program.Software engineeringAgents de codeDeveloper productivity+1
59:38EN
Jane Street· 18 mai 2023Richard Eisenberg on Dependent Types, OCaml, and AI-Assisted ProgrammingYaron Minsky, Richard Eisenberg · Jane StreetHow type systems can express correctness and performance, and why precise, readable specifications still matter when AI writes code.Software engineeringOpen-source ecosystemsAgents de code+1
41:40EN
No Priors: AI, Machine Learning, Tech, & Startups· 30 mars 2023Podcast · 2 voixEvery 10 Milliseconds Cost Copilot 1% of CompletionsAnime : Sarah Guo, Elad GilGitHub Copilot's chief architect, Alex Graveley, walks through how a leftover code model with a sub-10% test pass rate became a product developers would not quit — and what he is building next at Minion AI.Agents de codeProduct engineeringAI interface design+3
Charger plus24 sur 326 affichés